© 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. 56267
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting indicators

    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
    arty
    -0.07
    plist
    -0.07
     Lorem
    -0.06
    aux
    -0.06
    ocratic
    -0.06
     Gauss
    -0.06
    ucci
    -0.06
     Chavez
    -0.06
     ↵
    -0.06
    θεν
    -0.06
    POSITIVE LOGITS
    'gc
    0.08
    .MixedReality
    0.07
    üre
    0.07
     timeZone
    0.07
    /goto
    0.07
     SAFE
    0.07
    anzi
    0.07
    ÃŃnh
    0.06
     sami
    0.06
    xlsx
    0.06
    Activations Density 0.003%

    No Known Activations