© 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. 17-LLAMASCOPE-RES-131K
    11. 126643
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and data structures

    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
     Nag
    -0.07
    joy
    -0.07
    irit
    -0.06
    angl
    -0.06
    ear
    -0.06
    ussy
    -0.06
    oses
    -0.06
    Ease
    -0.06
    ẩu
    -0.06
    ike
    -0.06
    POSITIVE LOGITS
    lä
    0.07
    .jasper
    0.07
    embros
    0.07
    abela
    0.06
    oggler
    0.06
    æĤ
    0.06
    太éĥİ
    0.06
    /false
    0.06
    иÑĤоÑĢ
    0.06
    аÑĢÑĩ
    0.06
    Activations Density 0.019%

    No Known Activations