© 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. 85722
    Prev
    Next
    INDEX
    Explanations

    terms related to analysis and evaluation of data or concepts

    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
    idor
    -0.07
    ammen
    -0.06
    arus
    -0.06
    iken
    -0.06
    dbh
    -0.06
    à¸ļล
    -0.06
    ãĥ¼ãĥį
    -0.06
    udit
    -0.06
     cigarettes
    -0.06
    ispiel
    -0.06
    POSITIVE LOGITS
     light
    0.17
     context
    0.14
     Light
    0.14
    -light
    0.12
    Light
    0.12
    light
    0.12
    context
    0.12
     Context
    0.11
     contexto
    0.11
     LIGHT
    0.10
    Activations Density 0.082%

    No Known Activations