© 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. 62293
    Prev
    Next
    INDEX
    Explanations

    information regarding media releases and public warnings

    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¦
    -0.08
     or
    -0.06
    anson
    -0.06
    raison
    -0.06
    stagram
    -0.06
    (
    -0.06
    )..
    -0.06
    atsu
    -0.05
     mer
    -0.05
     stuff
    -0.05
    POSITIVE LOGITS
    à¥ĩà¤Ĥ↵
    0.09
    âĢ¦↵↵↵
    0.08
    åľ¨çº¿è§Ĩé¢ij
    0.08
    \brief
    0.08
    .updateDynamic
    0.07
    %)↵
    0.07
    .intellij
    0.07
    ëĶĶìĭľ
    0.07
     -*-č↵
    0.07
    (æ°´
    0.07
    Activations Density 0.044%

    No Known Activations