© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    references to quiz or trivia formats

    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
    eous
    -0.08
    edException
    -0.07
    olley
    -0.07
    chine
    -0.07
    acher
    -0.07
    üzel
    -0.07
    pour
    -0.07
     addCriterion
    -0.07
    chap
    -0.07
    eenth
    -0.07
    POSITIVE LOGITS
    ney
    0.08
    é¢ĺ
    0.07
     conducted
    0.07
    ster
    0.06
    consin
    0.06
    arel
    0.06
    otle
    0.06
    ette
    0.06
    ãĥ§
    0.06
    ark
    0.06
    Activations Density 0.002%

    No Known Activations