© 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. 104887
    Prev
    Next
    INDEX
    Explanations

    occurrences of the conjunction "and"

    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
    лÑıн
    -0.07
    ιÏĩ
    -0.07
     otherwise
    -0.07
    cxx
    -0.06
    ÑĢим
    -0.06
    Ä©
    -0.06
    ocument
    -0.06
    gom
    -0.06
    upal
    -0.06
    otherwise
    -0.06
    POSITIVE LOGITS
     enthusi
    0.07
     surtout
    0.07
    ibold
    0.07
     architekt
    0.06
    /or
    0.06
     budd
    0.06
    åħĪçĶŁ
    0.06
    LOC
    0.06
    atient
    0.06
    dek
    0.06
    Activations Density 0.008%

    No Known Activations