© 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. 77061
    Prev
    Next
    INDEX
    Explanations

    the concept of variation in different contexts or subjects

    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
    /player
    -0.07
    ì°©
    -0.07
    iska
    -0.07
    efeller
    -0.07
    chy
    -0.07
    ỳ
    -0.07
    à¥ĭह
    -0.07
    mé
    -0.07
    ald
    -0.07
    ISMATCH
    -0.06
    POSITIVE LOGITS
    iations
    0.10
    degrees
    0.10
    iable
    0.10
    iability
    0.09
    iances
    0.09
    iants
    0.08
     degrees
    0.08
    /var
    0.08
    ocities
    0.07
    rier
    0.07
    Activations Density 0.026%

    No Known Activations