© 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. 9-LLAMASCOPE-RES-131K
    11. 95708
    Prev
    Next
    INDEX
    Explanations

    references to equipment or gear-related terminology

    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
    bject
    -0.07
    -era
    -0.07
    kah
    -0.07
    aires
    -0.07
    kers
    -0.07
    kara
    -0.06
    /off
    -0.06
    enthal
    -0.06
    że
    -0.06
    oretical
    -0.06
    POSITIVE LOGITS
    igan
    0.09
    ë¡Ģ
    0.07
    uated
    0.07
    /software
    0.07
    lessness
    0.07
    lessly
    0.07
    iness
    0.07
    ikal
    0.07
    ling
    0.07
    iley
    0.07
    Activations Density 0.008%

    No Known Activations