© 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. 9-LLAMASCOPE-RES-131K
    11. 94592
    Prev
    Next
    INDEX
    Explanations

    academic abbreviations and designations

    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
     INTERRUPTION
    -0.07
     minim
    -0.06
    oose
    -0.06
    gs
    -0.06
    itzer
    -0.06
    /respond
    -0.05
    elen
    -0.05
     Tun
    -0.05
    nit
    -0.05
    çĶº
    -0.05
    POSITIVE LOGITS
    ovich
    0.07
    ardi
    0.07
    urus
    0.07
    :title
    0.06
    idi
    0.06
    orthy
    0.06
    .toolbox
    0.06
    kus
    0.06
    ÄĻki
    0.06
    shm
    0.06
    Activations Density 0.000%

    No Known Activations