© 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. 118528
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols that indicate separation or emphasis in the text

    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
    esc
    -0.08
    448
    -0.07
    æĬĢ
    -0.07
    λÏī
    -0.07
    .FieldName
    -0.07
    resolved
    -0.06
    assin
    -0.06
     Ùģت
    -0.06
    427
    -0.06
    assen
    -0.06
    POSITIVE LOGITS
     SetValue
    0.06
    üven
    0.06
    _initializer
    0.06
    åŀĤ
    0.06
     perv
    0.06
    chter
    0.06
    setItem
    0.05
    oppers
    0.05
    γο
    0.05
    .utility
    0.05
    Activations Density 0.000%

    No Known Activations