© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29272
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and chemical components

    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
    onso
    -0.08
    HAV
    -0.07
    oud
    -0.07
     ÑĢок
    -0.07
     hva
    -0.07
     ApplicationDbContext
    -0.07
    -ra
    -0.07
     Millet
    -0.07
     DateTimeKind
    -0.07
     ä¸
    -0.07
    POSITIVE LOGITS
    01
    0.06
     disc
    0.06
    05
    0.06
    UpDown
    0.06
    125
    0.06
    03
    0.06
    001
    0.06
    02
    0.06
    sume
    0.06
    ноÑģÑĤ
    0.06
    Activations Density 0.145%

    No Known Activations