© 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. 79357
    Prev
    Next
    INDEX
    Explanations

    comments or annotations within a code or document structure

    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
    sworth
    -0.08
    unden
    -0.07
     imper
    -0.07
     диви
    -0.07
    itage
    -0.07
    าà¸į
    -0.07
    uzey
    -0.07
     Jacqu
    -0.07
    ipop
    -0.07
    оÑĪ
    -0.07
    POSITIVE LOGITS
     Copyright
    0.08
    iere
    0.06
     copyright
    0.06
     Lind
    0.06
    Copyright
    0.06
    ière
    0.06
     SPDX
    0.06
    ousel
    0.06
    chap
    0.06
    %B
    0.06
    Activations Density 0.014%

    No Known Activations