© 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. 78806
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating potential actions or capabilities

    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
    egin
    -0.07
     tylko
    -0.06
    kb
    -0.06
    æīį
    -0.06
    SURE
    -0.06
    374
    -0.06
    леж
    -0.06
     Predict
    -0.06
    ele
    -0.06
    bek
    -0.06
    POSITIVE LOGITS
     even
    0.07
    odos
    0.07
    YLES
    0.07
    iddy
    0.07
    eti
    0.06
    _reporting
    0.06
    agger
    0.06
    801
    0.06
     be
    0.06
    ecure
    0.06
    Activations Density 0.044%

    No Known Activations