© 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. 107406
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotional connections related to identity

    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
    ube
    -0.06
    il
    -0.06
    eya
    -0.06
    .ColumnHeader
    -0.06
    inz
    -0.06
    WithString
    -0.06
    isz
    -0.06
    âm
    -0.05
     Typ
    -0.05
    ewing
    -0.05
    POSITIVE LOGITS
    owment
    0.08
    oldur
    0.07
    üçük
    0.07
     Saunders
    0.07
     YYS
    0.07
    enance
    0.07
     phÃŃ
    0.06
    aeper
    0.06
    eten
    0.06
    989
    0.06
    Activations Density 0.006%

    No Known Activations