© 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. 28740
    Prev
    Next
    INDEX
    Explanations

    HTML attribute values associated with classes and IDs

    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
    unn
    -0.07
    $__
    -0.07
    idl
    -0.07
    erer
    -0.06
    ous
    -0.06
     fier
    -0.06
    emann
    -0.06
     Fam
    -0.06
     claws
    -0.06
    oso
    -0.06
    POSITIVE LOGITS
    ula
    0.07
    rador
    0.06
    .FontStyle
    0.06
    ipa
    0.06
    aldi
    0.06
    ery
    0.06
    _ix
    0.06
    ¸ı
    0.06
    gene
    0.06
    villa
    0.06
    Activations Density 0.007%

    No Known Activations