© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71041
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and marital status

    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
    zn
    -0.08
    ichier
    -0.07
     mev
    -0.07
    orgot
    -0.06
    avras
    -0.06
     znam
    -0.06
    wers
    -0.06
    andom
    -0.06
    ongyang
    -0.06
    άβ
    -0.06
    POSITIVE LOGITS
    妻
    0.07
     paren
    0.07
     currently
    0.06
    932
    0.06
    recent
    0.06
     nit
    0.06
     Currently
    0.06
    _ele
    0.06
    RPC
    0.06
    married
    0.06
    Activations Density 0.015%

    No Known Activations