© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116640
    Prev
    Next
    INDEX
    Explanations

    code-related language constructs and specific programming patterns

    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
    .sul
    -0.07
    mlin
    -0.07
    mtree
    -0.07
    venta
    -0.07
    |RF
    -0.07
    aldo
    -0.07
    .FLAG
    -0.07
    åħį
    -0.07
    اساÙĨ
    -0.07
    ihan
    -0.06
    POSITIVE LOGITS
     Camel
    0.06
    ingular
    0.06
     singular
    0.06
    Dash
    0.06
    é©
    0.06
     underscores
    0.06
    ovna
    0.06
     Bah
    0.06
     formed
    0.06
    underscore
    0.06
    Activations Density 0.016%

    No Known Activations