© 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. 105954
    Prev
    Next
    INDEX
    Explanations

    details related to vehicle features and performance

    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
    angu
    -0.06
    enzhen
    -0.06
    uchen
    -0.06
    Addr
    -0.06
    ApplicationContext
    -0.06
    ingu
    -0.06
     vintage
    -0.05
    angan
    -0.05
    arrera
    -0.05
    ÄĽle
    -0.05
    POSITIVE LOGITS
    isen
    0.08
    (\'
    0.07
    _assign
    0.07
    ãĥ¥ãĥ¼
    0.07
    ;$
    0.07
    zes
    0.07
     SAMPLE
    0.06
     assignable
    0.06
     ASSIGN
    0.06
    íݸ
    0.06
    Activations Density 0.013%

    No Known Activations