© 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. 124275
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and emphasizes 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
     (__
    -0.06
    emailer
    -0.06
    /******/
    -0.06
    empt
    -0.06
    å®ħ
    -0.06
    incare
    -0.06
    plib
    -0.06
    ãĤ£
    -0.06
    mez
    -0.06
    xDB
    -0.06
    POSITIVE LOGITS
    ève
    0.08
    STALL
    0.07
    áž
    0.07
    utor
    0.07
    IMO
    0.07
    åĿĽ
    0.06
     Ree
    0.06
    utsche
    0.06
     ç¸
    0.06
    alth
    0.06
    Activations Density 0.004%

    No Known Activations