© 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. 75533
    Prev
    Next
    INDEX
    Explanations

    specific color-related items or descriptions

    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
    simd
    -0.07
    endid
    -0.07
    agan
    -0.07
    hausen
    -0.07
    getResponse
    -0.07
     dara
    -0.07
    ADI
    -0.07
    ỹ
    -0.07
    avax
    -0.07
     mdi
    -0.07
    POSITIVE LOGITS
     syndrome
    0.08
     Syndrome
    0.07
    /red
    0.07
    grams
    0.06
    igits
    0.06
    -bordered
    0.06
     Glob
    0.06
    guards
    0.06
     bail
    0.06
    lob
    0.05
    Activations Density 0.074%

    No Known Activations