© 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. 27473
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks and phrases that indicate speech or dialogue

    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
    Äįe
    -0.07
    ause
    -0.07
     Záp
    -0.07
    bers
    -0.07
    hea
    -0.07
    Å¡ek
    -0.06
     endregion
    -0.06
    ÃŃda
    -0.06
     Bans
    -0.06
    omer
    -0.06
    POSITIVE LOGITS
    odont
    0.07
    rame
    0.07
    weit
    0.06
    oretical
    0.06
    een
    0.06
     a
    0.06
    ноÑģи
    0.06
    isel
    0.06
    ãģĹãģĭ
    0.06
    jee
    0.06
    Activations Density 0.004%

    No Known Activations