© 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. 93994
    Prev
    Next
    INDEX
    Explanations

    scheduling and time-related details

    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
     Fah
    -0.06
    uffer
    -0.06
    cono
    -0.06
    734
    -0.06
    M
    -0.06
    abyrinth
    -0.06
     transparent
    -0.06
    hower
    -0.06
    nard
    -0.06
     trang
    -0.06
    POSITIVE LOGITS
    fak
    0.07
    'gc
    0.07
    Dims
    0.07
    åĨĬ
    0.07
    ë¡Ģ
    0.07
    isted
    0.07
    regon
    0.07
    UInteger
    0.07
    fol
    0.07
    Await
    0.07
    Activations Density 0.015%

    No Known Activations