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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129344
    Prev
    Next
    INDEX
    Explanations

    critical technical terms and action verbs related to programming or video games

    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
    Ưá»
    -0.07
    yleft
    -0.07
    colo
    -0.07
    getManager
    -0.07
    RAP
    -0.07
     trùng
    -0.06
    kok
    -0.06
    fork
    -0.06
    undra
    -0.06
    overlay
    -0.06
    POSITIVE LOGITS
     Early
    0.06
     implemented
    0.06
    Early
    0.06
     вд
    0.06
    thal
    0.06
     early
    0.06
     preliminary
    0.06
     Implemented
    0.06
    dorf
    0.06
    early
    0.06
    Activations Density 0.001%

    No Known Activations