© 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. 27110
    Prev
    Next
    INDEX
    Explanations

    structured actions or sequences in a narrative

    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
    raÄį
    -0.08
    kat
    -0.07
    apiro
    -0.07
    REFERRED
    -0.07
    kap
    -0.06
    xt
    -0.06
    iei
    -0.06
    etler
    -0.06
    related
    -0.06
    ia
    -0.06
    POSITIVE LOGITS
    ibName
    0.06
    okers
    0.06
     Secondary
    0.06
    pecia
    0.06
    ValueCollection
    0.06
    Rpc
    0.06
     secondary
    0.06
    $__
    0.06
    \Bundle
    0.06
    ugin
    0.05
    Activations Density 0.002%

    No Known Activations