© 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. 76220
    Prev
    Next
    INDEX
    Explanations

    punctuations and separators commonly used in written language

    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
    tics
    -0.08
     sque
    -0.07
    raquo
    -0.06
    онÑĮ
    -0.06
    thic
    -0.06
     Pear
    -0.06
    tsky
    -0.06
    ingleton
    -0.06
    804
    -0.05
    itoris
    -0.05
    POSITIVE LOGITS
    .foundation
    0.07
    .MixedReality
    0.07
    ÏģιÏĥÏĦ
    0.07
    arg
    0.07
    лÑĸв
    0.07
    exo
    0.07
     Cham
    0.06
    _KP
    0.06
    cete
    0.06
    spl
    0.06
    Activations Density 0.002%

    No Known Activations