© 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. 81488
    Prev
    Next
    INDEX
    Explanations

    specific structures and formats in textual data, particularly in code or programming contexts

    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
    ardash
    -0.07
    μβ
    -0.07
    lsru
    -0.07
    Å¡
    -0.06
    plier
    -0.06
    ìī¬
    -0.06
    _pb
    -0.06
    achinery
    -0.06
    rž
    -0.06
    á»·
    -0.06
    POSITIVE LOGITS
    İ
    0.10
    200
    0.08
    190
    0.08
    10
    0.08
    estroy
    0.07
    ĥĿ
    0.07
    deaux
    0.07
     Gord
    0.07
    ¸ı
    0.07
    20
    0.07
    Activations Density 0.065%

    No Known Activations