© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75769
    Prev
    Next
    INDEX
    Explanations

    brackets and parentheses in the 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
    ole
    -0.08
    alama
    -0.07
    .react
    -0.06
    ![
    -0.06
    .ps
    -0.06
    ulis
    -0.06
    umber
    -0.06
    ç¯
    -0.06
    kul
    -0.06
    uh
    -0.06
    POSITIVE LOGITS
     Far
    0.07
    raquo
    0.07
    etooth
    0.07
     Elder
    0.07
     Eld
    0.07
     odense
    0.07
    Far
    0.07
    Misc
    0.06
    specified
    0.06
    wards
    0.06
    Activations Density 0.022%

    No Known Activations