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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 5667
    Prev
    Next
    INDEX
    Explanations

    references to access and permissions in a technical context, often related to databases or software systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ationToken
    -0.17
    utex
    -0.15
    aring
    -0.15
    ales
    -0.15
    433
    -0.15
    .converter
    -0.14
     lÃłnh
    -0.14
    ish
    -0.14
    echa
    -0.14
    venir
    -0.14
    POSITIVE LOGITS
    ibly
    0.37
    ions
    0.30
    orial
    0.29
    ible
    0.28
    IBLE
    0.26
    sing
    0.25
    ories
    0.25
    ory
    0.25
    ibility
    0.24
    ibilities
    0.24
    Activations Density 0.038%

    No Known Activations