© 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. 16-LLAMASCOPE-RES-32K
    11. 9289
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "share" and related terms indicating the act of sharing or collective possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owanie
    -0.15
    коÑĤ
    -0.15
    éĬ
    -0.14
    ovu
    -0.14
    ãĥ¼ãĥį
    -0.14
    го
    -0.14
    chein
    -0.14
    amat
    -0.14
     ëĨ
    -0.14
    ukt
    -0.14
    POSITIVE LOGITS
    /shared
    0.23
     sharing
    0.19
     shared
    0.19
     responsibility
    0.19
     shares
    0.18
    fax
    0.17
     share
    0.17
     Responsibility
    0.17
    share
    0.17
    (shared
    0.16
    Activations Density 0.045%

    No Known Activations