© 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. 119429
    Prev
    Next
    INDEX
    Explanations

    references to online accessibility of documents and resources

    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
    çı
    -0.06
    513
    -0.06
    Sorted
    -0.05
    ãĥªãĤ¢
    -0.05
     hung
    -0.05
     Fires
    -0.05
    pekt
    -0.05
    à¸Ľà¸¥
    -0.05
    lesi
    -0.05
     Cert
    -0.05
    POSITIVE LOGITS
    .ACCESS
    0.08
    коп
    0.07
    astreet
    0.07
    надлеж
    0.07
    errer
    0.07
    esub
    0.07
    yh
    0.07
    accessible
    0.07
    ement
    0.07
    _abstract
    0.07
    Activations Density 0.012%

    No Known Activations