© 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. 17-LLAMASCOPE-RES-131K
    11. 87066
    Prev
    Next
    INDEX
    Explanations

    types and templates in programming code

    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
    blade
    -0.07
    ahy
    -0.07
     Pla
    -0.07
    imei
    -0.06
     pla
    -0.06
    licht
    -0.06
     forget
    -0.06
    imoto
    -0.06
    ÑģÑĤÑĢи
    -0.06
    lex
    -0.06
    POSITIVE LOGITS
    ##_
    0.11
    üzel
    0.07
    lant
    0.06
    ustos
    0.06
    trag
    0.06
    åŀĭ
    0.06
    κÏģι
    0.06
    +'_
    0.06
    _Impl
    0.06
    /as
    0.06
    Activations Density 0.004%

    No Known Activations