© 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. 89299
    Prev
    Next
    INDEX
    Explanations

    references to actions or states

    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
    Gratis
    -0.07
    pent
    -0.07
    alian
    -0.06
    ogeneous
    -0.06
    ickers
    -0.06
    amin
    -0.06
     Cutter
    -0.06
    éĹ
    -0.06
     Genetics
    -0.06
     phys
    -0.06
    POSITIVE LOGITS
    iyon
    0.08
    nik
    0.06
    že
    0.06
    sko
    0.06
     defaultMessage
    0.06
    θμ
    0.06
    bine
    0.06
    _utilities
    0.06
    (SC
    0.06
    fv
    0.06
    Activations Density 0.001%

    No Known Activations