© 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. 74056
    Prev
    Next
    INDEX
    Explanations

    punctuation and the structure of sentences

    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
    .toolbox
    -0.07
     hubby
    -0.06
    =back
    -0.06
    TOTYPE
    -0.06
    ei
    -0.06
    Äįe
    -0.06
    æľ
    -0.06
    åģ¥
    -0.06
    Iron
    -0.06
    /wiki
    -0.06
    POSITIVE LOGITS
    ulia
    0.08
    VICE
    0.08
    λÏī
    0.08
    ersions
    0.08
     fuck
    0.08
    osl
    0.07
     GIF
    0.07
     Fuck
    0.07
    dorf
    0.07
    phin
    0.07
    Activations Density 0.046%

    No Known Activations