© 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. 38852
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting in written text

    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
    ÃŃrk
    -0.07
    tember
    -0.07
    kazy
    -0.07
    addock
    -0.07
    αν
    -0.07
    ledon
    -0.07
    zac
    -0.07
     Gomez
    -0.07
    Enlarge
    -0.07
    HOOK
    -0.07
    POSITIVE LOGITS
     chapter
    0.08
    aci
    0.07
     Chapter
    0.06
    cape
    0.06
    .toolbox
    0.06
    Chapter
    0.06
    uby
    0.06
    иÑĤÑĭ
    0.06
     append
    0.06
    ator
    0.06
    Activations Density 0.001%

    No Known Activations