© 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. 41321
    Prev
    Next
    INDEX
    Explanations

    terms related to health, safety, and production management

    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
    }elseif
    -0.07
    uml
    -0.07
     resil
    -0.06
    atitis
    -0.06
    tok
    -0.06
     promin
    -0.06
    ноз
    -0.06
    bye
    -0.06
    ASET
    -0.06
    ãģ¨ãģĨ
    -0.06
    POSITIVE LOGITS
    мини
    0.07
    REM
    0.07
    ebin
    0.07
    ombat
    0.07
    asje
    0.06
     tale
    0.06
    unker
    0.06
    ebek
    0.06
    ABI
    0.06
    ymb
    0.06
    Activations Density 0.195%

    No Known Activations