© 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. 87588
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation used in code and markup

    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
    idl
    -0.07
    arde
    -0.07
    eyin
    -0.07
    oice
    -0.07
    ripple
    -0.07
    issen
    -0.06
    deme
    -0.06
    ceae
    -0.06
    icher
    -0.06
    VECTOR
    -0.06
    POSITIVE LOGITS
     such
    0.07
     ÙħÙĩر
    0.06
     Colomb
    0.06
    921
    0.06
     Gravity
    0.06
     Hansen
    0.06
     bod
    0.06
     Hab
    0.06
    /doc
    0.06
     NGX
    0.05
    Activations Density 0.000%

    No Known Activations