© 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. 15-LLAMASCOPE-RES-131K
    11. 89916
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly semicolons and brackets

    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
    drv
    -0.07
    òn
    -0.07
     ion
    -0.06
     Ion
    -0.06
    ần
    -0.06
    reature
    -0.06
    erson
    -0.06
    759
    -0.06
     Han
    -0.06
    IMG
    -0.06
    POSITIVE LOGITS
    ixe
    0.06
    rup
    0.06
    eed
    0.06
    abs
    0.06
     numberWith
    0.06
     gön
    0.06
    wayne
    0.06
    endar
    0.06
    jes
    0.06
    à¥Īà¤łà¤ķ
    0.06
    Activations Density 0.000%

    No Known Activations