© 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. 81608
    Prev
    Next
    INDEX
    Explanations

    references to different versions or updates of software

    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
    obi
    -0.07
    ÑĩаÑģ
    -0.07
    la
    -0.07
    ãģĬãĤĬ
    -0.07
    reich
    -0.07
    ãģªãģĮãĤī
    -0.07
    ang
    -0.07
    zelf
    -0.07
     res
    -0.07
    rev
    -0.07
    POSITIVE LOGITS
    able
    0.09
    ables
    0.09
    oire
    0.08
    /release
    0.08
    aire
    0.08
    nofollow
    0.08
    ABEL
    0.07
    ible
    0.07
    azer
    0.07
    .Release
    0.07
    Activations Density 0.025%

    No Known Activations