© 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. 57098
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of interest or inquiry

    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
    ison
    -0.07
    PLUGIN
    -0.06
    ibo
    -0.06
    ÑĤÑĶ
    -0.06
     Resort
    -0.06
     Dense
    -0.06
    fault
    -0.06
    ihn
    -0.06
     Tube
    -0.06
    ently
    -0.06
    POSITIVE LOGITS
     interest
    0.08
     possibility
    0.08
     willing
    0.07
    RLF
    0.07
     interested
    0.07
    é¡ĺ
    0.07
    orks
    0.07
     Interest
    0.07
     willingness
    0.07
    oÄŁ
    0.07
    Activations Density 0.013%

    No Known Activations