© 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. 126602
    Prev
    Next
    INDEX
    Explanations

    references to blog posts or episodes

    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
    chio
    -0.08
    rech
    -0.06
    ing
    -0.06
    708
    -0.06
    äm
    -0.06
    161
    -0.06
    lein
    -0.06
    _ordered
    -0.06
    293
    -0.06
    424
    -0.06
    POSITIVE LOGITS
    ONTAL
    0.08
    Untitled
    0.08
    (éĩij
    0.07
    awy
    0.07
    theid
    0.07
    ÙĥÙĬÙĬÙģ
    0.07
    бÑĢÑı
    0.07
     Aires
    0.07
    XHR
    0.07
     ++)↵
    0.07
    Activations Density 0.002%

    No Known Activations