© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74887
    Prev
    Next
    INDEX
    Explanations

    mentions of notable political figures, particularly Nancy Pelosi

    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
     yyn
    -0.07
    ALSE
    -0.07
    zek
    -0.07
    ÑĥÑĢи
    -0.07
    zos
    -0.06
    rung
    -0.06
     biên
    -0.06
    ůr
    -0.06
    urret
    -0.06
     addCriterion
    -0.06
    POSITIVE LOGITS
     San
    0.09
    San
    0.07
     Baltimore
    0.07
     san
    0.07
     Shan
    0.06
     SF
    0.06
    SAN
    0.06
     Irish
    0.06
     SAN
    0.06
     sched
    0.06
    Activations Density 0.004%

    No Known Activations