© 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. 83182
    Prev
    Next
    INDEX
    Explanations

    JavaScript or jQuery methods used for DOM manipulation

    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
    aze
    -0.08
    achi
    -0.07
    ensch
    -0.07
    stÃŃ
    -0.07
    undance
    -0.07
    inals
    -0.07
    fusion
    -0.07
    tainment
    -0.07
     lut
    -0.06
    IDGET
    -0.06
    POSITIVE LOGITS
    ((-
    0.07
     plugged
    0.06
     curtain
    0.06
    478
    0.06
     defer
    0.06
     liable
    0.06
    olean
    0.06
     div
    0.06
    warz
    0.06
     Crit
    0.05
    Activations Density 0.003%

    No Known Activations