© 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 EvalsExportsAPI 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. 118688
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to text processing and manipulation

    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
    ÙĪز
    -0.07
    лин
    -0.07
    .slim
    -0.07
    adh
    -0.07
    _UTILS
    -0.07
    .lu
    -0.07
    xec
    -0.07
    Knife
    -0.07
    ÏĦεÏį
    -0.07
    endi
    -0.06
    POSITIVE LOGITS
    AMI
    0.07
     circum
    0.06
     gender
    0.06
     capit
    0.06
     raised
    0.06
     Buck
    0.06
     crashed
    0.05
     special
    0.05
    rophy
    0.05
     Invent
    0.05
    Activations Density 0.007%

    No Known Activations