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

    Neuronpedia

    Jacobian LensNEW
    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. 87927
    Prev
    Next
    INDEX
    Explanations

    legal or formal language related to patents and documents

    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
    ining
    -0.06
     buck
    -0.06
    SP
    -0.06
    mq
    -0.06
    oret
    -0.06
    odus
    -0.06
     Cru
    -0.06
    rž
    -0.06
    olicit
    -0.06
    indi
    -0.06
    POSITIVE LOGITS
     requestOptions
    0.07
    UTO
    0.07
    IZER
    0.07
    oust
    0.07
    eler
    0.07
    antha
    0.06
    ilor
    0.06
    porte
    0.06
    GenerationStrategy
    0.06
    tera
    0.06
    Activations Density 0.008%

    No Known Activations