© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87153
    Prev
    Next
    INDEX
    Explanations

    phrases associated with functionality and outcomes in technical instructions

    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
    alue
    -0.07
    luet
    -0.07
    grese
    -0.07
    chner
    -0.06
    acceptable
    -0.06
    asant
    -0.06
    ROI
    -0.06
    oi
    -0.06
    ноÑĪ
    -0.06
    elas
    -0.06
    POSITIVE LOGITS
     automatically
    0.10
     automatic
    0.08
     immediately
    0.07
     immediate
    0.07
    èĩªåĬ¨
    0.06
     instantly
    0.06
     ìŀIJëıĻ
    0.06
     autom
    0.06
     Automatic
    0.06
     automáticamente
    0.06
    Activations Density 0.023%

    No Known Activations