© 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. 60869
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts and financial obligations

    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
     drag
    -0.07
    ELS
    -0.06
     fore
    -0.06
    defer
    -0.06
    onna
    -0.06
    .Messages
    -0.06
    ï¼ł
    -0.06
    739
    -0.06
    iyas
    -0.06
    ahy
    -0.06
    POSITIVE LOGITS
    uppen
    0.07
    dish
    0.06
    .ElementAt
    0.06
    éĻ£
    0.06
    iders
    0.06
    idla
    0.06
     ARTICLE
    0.06
    itet
    0.06
    ationToken
    0.06
    writer
    0.06
    Activations Density 0.021%

    No Known Activations