© 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. 78206
    Prev
    Next
    INDEX
    Explanations

    references to pregnancy and pregnant individuals

    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
    aley
    -0.08
     knÃŃ
    -0.07
    obo
    -0.07
    agher
    -0.07
    ipzig
    -0.07
    ponent
    -0.07
    agara
    -0.07
    Eigen
    -0.06
     kÃ¶ÅŁ
    -0.06
    oger
    -0.06
    POSITIVE LOGITS
    ness
    0.08
    892
    0.07
    nes
    0.07
     women
    0.06
     ones
    0.06
    abei
    0.06
     GOODMAN
    0.06
    ict
    0.06
    /raw
    0.06
    icted
    0.06
    Activations Density 0.003%

    No Known Activations