© 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. 5-LLAMASCOPE-RES-131K
    11. 126497
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reason."

    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
    umba
    -0.07
    ansson
    -0.06
    ered
    -0.06
    eba
    -0.06
    esa
    -0.06
    zap
    -0.06
     Heard
    -0.06
    nda
    -0.06
     Sustainable
    -0.06
    ossal
    -0.06
    POSITIVE LOGITS
    nova
    0.07
    anova
    0.06
    olith
    0.06
    affer
    0.06
    allah
    0.06
    liest
    0.06
    adel
    0.06
    olithic
    0.06
    lica
    0.06
    Phys
    0.06
    Activations Density 0.000%

    No Known Activations