© 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. 3718
    Prev
    Next
    INDEX
    Explanations

    references to crises or critical situations impacting society

    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
    cheng
    -0.08
    uchar
    -0.07
     addCriterion
    -0.07
    ceived
    -0.07
    .UnitTesting
    -0.07
    enso
    -0.06
    nemonic
    -0.06
    تÙĦ
    -0.06
    chap
    -0.06
    jie
    -0.06
    POSITIVE LOGITS
    mer
    0.08
    agnostics
    0.07
     situation
    0.07
    (es
    0.07
    /question
    0.07
    ichel
    0.07
    pped
    0.07
     situations
    0.07
    ÙĨاÙħÙĩ
    0.06
     Prevention
    0.06
    Activations Density 0.008%

    No Known Activations