© 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. 30805
    Prev
    Next
    INDEX
    Explanations

    lines of code that perform variable assignments

    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
    eldorf
    -0.07
    andelier
    -0.07
    berman
    -0.07
     McDon
    -0.06
    /vnd
    -0.06
    ottom
    -0.06
    otal
    -0.06
    faker
    -0.06
    umbn
    -0.06
    unya
    -0.06
    POSITIVE LOGITS
    eh
    0.07
    ument
    0.06
    ab
    0.06
    AINS
    0.06
    IPH
    0.06
    енÑı
    0.06
    Dev
    0.06
    ats
    0.06
    ÑĢоб
    0.06
    _null
    0.06
    Activations Density 0.002%

    No Known Activations