© 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. 17-LLAMASCOPE-RES-131K
    11. 61890
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦)
    -0.07
    =”
    -0.07
     ‘
    -0.06
    Ìģ
    -0.06
    esis
    -0.06
    µľ
    -0.06
    :↵↵↵↵
    -0.06
    $/,
    -0.06
    \_
    -0.06
    edit
    -0.06
    POSITIVE LOGITS
    .gstatic
    0.07
     {}".
    0.07
     appendString
    0.06
    ptal
    0.06
     noqa
    0.06
     {}'.
    0.06
    å¼¥
    0.06
    aminer
    0.06
    .dataTables
    0.06
    MAND
    0.06
    Activations Density 0.093%

    No Known Activations