© 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. 118122
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and variable names

    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
    dro
    -0.06
    .ly
    -0.06
    ypi
    -0.06
    omm
    -0.06
    Orm
    -0.06
    OOM
    -0.06
    ipa
    -0.06
     drift
    -0.06
     eb
    -0.06
    ãĥĸ
    -0.06
    POSITIVE LOGITS
    %C
    0.10
     queryInterface
    0.07
    actionDate
    0.07
     (↵↵
    0.07
    #aa
    0.07
    uniacid
    0.07
    rescia
    0.07
     addCriterion
    0.07
    /browse
    0.07
    ¦y
    0.07
    Activations Density 0.003%

    No Known Activations