© 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. 83295
    Prev
    Next
    INDEX
    Explanations

    computer programming and installation 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
     Crosby
    -0.07
    lov
    -0.07
     Bing
    -0.07
    jmu
    -0.07
    åĸ
    -0.07
    eger
    -0.07
    ernel
    -0.07
    erin
    -0.06
    rike
    -0.06
    wo
    -0.06
    POSITIVE LOGITS
     dist
    0.07
     environment
    0.07
     environments
    0.07
     virtual
    0.07
    conda
    0.06
     Virtual
    0.06
    ContextHolder
    0.06
    etto
    0.06
     Shack
    0.06
     development
    0.06
    Activations Density 0.104%

    No Known Activations