© 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. 125988
    Prev
    Next
    INDEX
    Explanations

    terms related to public health initiatives and gender considerations

    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
    prend
    -0.07
     dint
    -0.06
    uiten
    -0.06
     Nich
    -0.06
    gener
    -0.06
    raq
    -0.06
    odka
    -0.06
     gener
    -0.06
    fc
    -0.06
     preventative
    -0.06
    POSITIVE LOGITS
    haps
    0.08
     should
    0.08
     perhaps
    0.08
    igham
    0.07
    озможно
    0.07
     future
    0.07
    should
    0.07
    彦
    0.07
    perhaps
    0.07
    aybe
    0.06
    Activations Density 0.038%

    No Known Activations