© 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 EvalsExportsinterp-engineNEWAPI 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. 124417
    Prev
    Next
    INDEX
    Explanations

    themes related to significant qualities and characteristics of entities or situations

    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
     åĽ
    -0.08
    htt
    -0.07
    meli
    -0.07
    ẽ
    -0.07
    iyim
    -0.07
    AGMA
    -0.07
     èĴ
    -0.07
    ãĤ
    -0.07
    -eslint
    -0.07
    ữ
    -0.07
    POSITIVE LOGITS
     operative
    0.06
    Keywords
    0.06
     BaseService
    0.06
    eken
    0.06
    ken
    0.06
    åĿĤ
    0.06
     abound
    0.06
     key
    0.06
    .keywords
    0.05
     mode
    0.05
    Activations Density 0.031%

    No Known Activations