© 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. 4967
    Prev
    Next
    INDEX
    Explanations

    phrases referring to the movement or transfer of items or information

    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
    kö
    -0.07
    URY
    -0.07
    uf
    -0.06
     bordel
    -0.06
    alo
    -0.06
    yt
    -0.06
    ury
    -0.06
     Miscellaneous
    -0.06
    {}".
    -0.06
    WithURL
    -0.06
    POSITIVE LOGITS
    /to
    0.10
     Ø¥ÙĦÙī
    0.08
    igans
    0.07
     اÙĦÙī
    0.07
    ÏĦÏģα
    0.07
     one
    0.07
    bler
    0.07
    ään
    0.07
    å¨
    0.07
     rá»Ŀi
    0.07
    Activations Density 0.032%

    No Known Activations