© 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. 16594
    Prev
    Next
    INDEX
    Explanations

    collections or groupings of items or ideas

    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
    Įĵ
    -0.07
    Ð
    -0.06
     Edition
    -0.06
    دار
    -0.06
    och
    -0.06
     Bolt
    -0.06
     Cue
    -0.06
    Edition
    -0.06
    OTA
    -0.06
    .ws
    -0.05
    POSITIVE LOGITS
    CloseOperation
    0.06
    .BLL
    0.06
    atto
    0.06
    cin
    0.06
    ente
    0.06
    atham
    0.06
    aud
    0.06
    umin
    0.06
     atmospheric
    0.06
    /cpp
    0.06
    Activations Density 0.008%

    No Known Activations