© 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. 86157
    Prev
    Next
    INDEX
    Explanations

    prompts and elements related to user interaction and comments

    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
    atham
    -0.07
    atsu
    -0.07
     cứng
    -0.07
     sk
    -0.06
     mặt
    -0.06
     drum
    -0.06
    á»Ĺ
    -0.06
    ynch
    -0.06
    VP
    -0.06
    .gl
    -0.06
    POSITIVE LOGITS
     comment
    0.14
     comments
    0.13
     COMMENTS
    0.13
     Comment
    0.13
    comments
    0.12
     Comments
    0.12
    Comments
    0.11
     COMMENT
    0.11
    .comment
    0.10
     commenting
    0.10
    Activations Density 0.016%

    No Known Activations