© 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. 87328
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly those that denote the end of sentences

    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
    endencies
    -0.08
    @qq
    -0.08
    uggage
    -0.08
    ifecycle
    -0.07
    :Register
    -0.07
    elpers
    -0.07
    ULLET
    -0.07
    edException
    -0.07
    undles
    -0.07
     SetLastError
    -0.07
    POSITIVE LOGITS
    s
    0.07
    ones
    0.06
     yet
    0.06
    xD
    0.06
    a
    0.06
     Compet
    0.06
    Å¡ak
    0.06
    som
    0.06
    e
    0.06
     Conserv
    0.06
    Activations Density 0.042%

    No Known Activations