© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    programming constructs and logical conditions

    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
    toi
    -0.07
    ilon
    -0.07
    ût
    -0.07
    oug
    -0.07
    itung
    -0.07
    alion
    -0.07
    lep
    -0.06
    zon
    -0.06
    ohen
    -0.06
    @nate
    -0.06
    POSITIVE LOGITS
    Ĩ
    0.07
    884
    0.06
    726
    0.06
     Guy
    0.06
    259
    0.06
    048
    0.06
    509
    0.06
     spread
    0.06
     spreads
    0.06
    105
    0.06
    Activations Density 0.003%

    No Known Activations