© 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. 87927
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly those that represent the structure and syntax of code

    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
    tsky
    -0.08
    åĽ³
    -0.07
    ",__
    -0.07
    份
    -0.07
    ÑĥлÑı
    -0.07
    ecycle
    -0.07
    ycop
    -0.06
     rady
    -0.06
    717
    -0.06
    achuset
    -0.06
    POSITIVE LOGITS
    DMI
    0.07
     //{↵
    0.06
     dri
    0.06
    .orange
    0.06
     Goodman
    0.06
     Til
    0.05
    ional
    0.05
     heter
    0.05
     Glen
    0.05
     goose
    0.05
    Activations Density 0.015%

    No Known Activations