© 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 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. 4-LLAMASCOPE-RES-32K
    11. 32219
    Prev
    Next
    INDEX
    Explanations

    conjunctions and reference words indicating connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    浦
    -0.16
    asts
    -0.15
    unan
    -0.15
    é«
    -0.14
     både
    -0.14
     allerdings
    -0.14
    ightly
    -0.14
    âħ
    -0.13
    onian
    -0.13
    ruc
    -0.13
    POSITIVE LOGITS
    /or
    0.61
    /of
    0.28
    rogen
    0.27
    rew
    0.27
    /OR
    0.26
    наÑĩе
    0.25
    rog
    0.22
    rea
    0.21
    /o
    0.21
    nbsp
    0.21
    Activations Density 1.943%

    No Known Activations