© 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. 15-LLAMASCOPE-RES-131K
    11. 103712
    Prev
    Next
    INDEX
    Explanations

    specific car models and related automotive terms

    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
    nex
    -0.07
    ernel
    -0.07
    quine
    -0.06
    oner
    -0.06
     Nylon
    -0.06
    uco
    -0.06
     spills
    -0.06
     gá»Ĺ
    -0.06
    nou
    -0.06
     lParam
    -0.06
    POSITIVE LOGITS
    产
    0.07
    antro
    0.07
    haar
    0.07
    -initialized
    0.06
    amenti
    0.06
    áp
    0.06
    mony
    0.06
    deÅŁ
    0.06
    uldu
    0.06
    миÑĢ
    0.06
    Activations Density 0.004%

    No Known Activations