© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 11448
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing tags in XML/HTML markup.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    end-of-element markers in structured markup/code, especially closing tags in XML/HTML-like lists and UI components.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anta
    -0.15
    ikh
    -0.14
    odel
    -0.13
     kâ
    -0.13
    llu
    -0.13
    éģĬ
    -0.13
    ibu
    -0.13
    ogle
    -0.12
    ushman
    -0.12
    _RETURN
    -0.12
    POSITIVE LOGITS
    .lt
    0.15
    aro
    0.13
    aron
    0.13
    autos
    0.13
    ather
    0.13
    946
    0.13
    _clr
    0.13
    robat
    0.12
     McCl
    0.12
    apo
    0.12
    Activations Density 0.050%

    No Known Activations