© 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. 85991
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connecting phrases that indicate lists or sequences

    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
    ÑĤал
    -0.07
    ãĥ´
    -0.06
    .opend
    -0.06
    ãĥ©ãĥ³ãĥī
    -0.06
    ضÙĦ
    -0.06
     tha
    -0.06
    ÏĦεÏģ
    -0.06
    Ïħκ
    -0.06
     Frequently
    -0.06
    arn
    -0.06
    POSITIVE LOGITS
     yoksa
    0.07
    owitz
    0.07
    auty
    0.06
     entirety
    0.06
    heimer
    0.06
    ovit
    0.06
    ledge
    0.06
    cc
    0.06
    -----------↵↵
    0.06
    ope
    0.06
    Activations Density 0.055%

    No Known Activations