© 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. 62633
    Prev
    Next
    INDEX
    Explanations

    terms related to birth and birth records

    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
    ç«ĭãģ¦
    -0.07
    zzo
    -0.07
    .PERMISSION
    -0.07
    à¸Ĥ
    -0.07
    itis
    -0.07
    owa
    -0.07
    ALAR
    -0.06
    urator
    -0.06
    ÑĩаÑģÑĤ
    -0.06
     unre
    -0.06
    POSITIVE LOGITS
    place
    0.09
    rets
    0.07
    esda
    0.07
    places
    0.07
    date
    0.07
    lehem
    0.07
    DAY
    0.07
    days
    0.07
    rate
    0.06
    ussy
    0.06
    Activations Density 0.009%

    No Known Activations