© 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. 15-LLAMASCOPE-RES-131K
    11. 26942
    Prev
    Next
    INDEX
    Explanations

    phrases indicating justification or explanation

    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
    raith
    -0.07
    odb
    -0.07
    ughter
    -0.06
    endum
    -0.06
    IVITY
    -0.06
    -0.06
    βε
    -0.06
    UGE
    -0.06
    .logging
    -0.06
    ypsum
    -0.06
    POSITIVE LOGITS
     anymore
    0.07
     necessarily
    0.07
     merely
    0.07
    standing
    0.07
     nor
    0.07
    mere
    0.07
    acher
    0.07
     because
    0.06
     obviously
    0.06
    Parms
    0.06
    Activations Density 0.018%

    No Known Activations