© 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. 72760
    Prev
    Next
    INDEX
    Explanations

    references to the Grand Army and its associated history and records

    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
    oulouse
    -0.07
    ecta
    -0.07
    morgan
    -0.07
     WINDOWS
    -0.07
    تÙĩا
    -0.07
     иÑģк
    -0.07
    NetMessage
    -0.07
    ANI
    -0.07
    ãĥ¬ãĤ¹
    -0.07
    \Schema
    -0.07
    POSITIVE LOGITS
    ox
    0.07
    186
    0.07
     Railroad
    0.06
    HD
    0.06
    187
    0.06
    184
    0.06
    183
    0.06
     masc
    0.06
     él
    0.06
     underage
    0.06
    Activations Density 0.003%

    No Known Activations