© 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. 39026
    Prev
    Next
    INDEX
    Explanations

    components and structures in descriptions of physical objects or systems

    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
    ³
    -0.06
    edb
    -0.06
    teil
    -0.06
    ستÙħ
    -0.06
    BuilderFactory
    -0.06
    bir
    -0.06
    878
    -0.06
    شت
    -0.06
    ngth
    -0.05
    rb
    -0.05
    POSITIVE LOGITS
    pseudo
    0.07
    rops
    0.07
    ả
    0.07
    ãĤīãģĽ
    0.07
    лÑĸÑĤ
    0.07
    ploy
    0.07
    'gc
    0.07
    ORK
    0.07
     conv
    0.06
    gaben
    0.06
    Activations Density 0.048%

    No Known Activations