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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61439
    Prev
    Next
    INDEX
    Explanations

    references to specific sections and mathematical definitions within a technical document

    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
    evenodd
    -0.07
    #ga
    -0.07
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.07
    /gpl
    -0.07
    èĨľ
    -0.07
    ObjectContext
    -0.07
     helicopt
    -0.06
    골
    -0.06
    /rand
    -0.06
    ìĦĿ
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    alian
    0.06
    >{@
    0.06
    uml
    0.06
    ugar
    0.06
    uito
    0.06
    liers
    0.06
    ains
    0.06
    ury
    0.06
    tol
    0.06
    Activations Density 0.025%

    No Known Activations