© 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. 54843
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, indicating the end of statements

    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
     system
    -0.07
    867
    -0.06
     System
    -0.06
    atta
    -0.06
    rg
    -0.06
     jud
    -0.06
    anga
    -0.06
    913
    -0.06
     pe
    -0.05
    hu
    -0.05
    POSITIVE LOGITS
    ervo
    0.08
    -corner
    0.07
    dsn
    0.07
     strokeLine
    0.07
    /renderer
    0.07
    hack
    0.07
    ediator
    0.07
     tents
    0.07
    åŃ
    0.07
    erea
    0.07
    Activations Density 0.001%

    No Known Activations