© 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. 79749
    Prev
    Next
    INDEX
    Explanations

    punctuations and markup syntax commonly used in coding and documentation

    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
    pes
    -0.06
    ilis
    -0.06
    appers
    -0.06
    Ñĸз
    -0.06
    ipers
    -0.06
    оÑĩек
    -0.06
    estar
    -0.06
    erland
    -0.06
    ityEngine
    -0.06
    ells
    -0.06
    POSITIVE LOGITS
    ordova
    0.07
     wet
    0.06
     astr
    0.06
    kre
    0.06
    geist
    0.06
    ONA
    0.06
     flagged
    0.06
     Ranch
    0.06
    .assertj
    0.06
    _bulk
    0.06
    Activations Density 0.015%

    No Known Activations