© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41203
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to items or concepts that are consistent or repetitive

    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
    zell
    -0.07
    placeholders
    -0.07
    liš
    -0.07
    etros
    -0.07
     place
    -0.07
    екÑĤ
    -0.07
    OURCES
    -0.07
    åĩĿ
    -0.06
    ipse
    -0.06
     Graz
    -0.06
    POSITIVE LOGITS
     ilk
    0.07
     sorts
    0.07
    erta
    0.07
    ##_
    0.07
    alty
    0.07
     workforce
    0.06
    PREC
    0.06
    otel
    0.06
    okin
    0.06
    @protocol
    0.06
    Activations Density 0.038%

    No Known Activations