© 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. 117267
    Prev
    Next
    INDEX
    Explanations

    concepts related to educational research and inclusivity

    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
    aval
    -0.08
    Population
    -0.06
    itta
    -0.06
    rei
    -0.06
    achi
    -0.06
    assa
    -0.06
    ÄĻ
    -0.06
    ãģĨãģ¡
    -0.06
    çľł
    -0.06
    leme
    -0.06
    POSITIVE LOGITS
     UNESCO
    0.07
     Lantern
    0.07
     Mezi
    0.07
    emouth
    0.07
    UGHT
    0.07
    Ñģли
    0.07
     Zy
    0.07
     Paulo
    0.06
    Å¡t
    0.06
    swick
    0.06
    Activations Density 0.024%

    No Known Activations