© 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 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. 118698
    Prev
    Next
    INDEX
    Explanations

    URLs or links to web content

    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
    pa
    -0.07
     vain
    -0.06
    uevo
    -0.06
     dim
    -0.06
    chio
    -0.06
    fo
    -0.06
    ats
    -0.06
    _rom
    -0.06
    /page
    -0.06
    naire
    -0.06
    POSITIVE LOGITS
    ENDER
    0.07
    (Source
    0.07
    ://
    0.07
    353
    0.07
    outu
    0.07
     Rubin
    0.07
    fon
    0.07
    ElementsBy
    0.06
    elman
    0.06
    Äħż
    0.06
    Activations Density 0.003%

    No Known Activations