© 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. 29052
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jenny."

    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
    utter
    -0.07
    æ´²
    -0.06
    ÅĽmy
    -0.06
    HandlerContext
    -0.06
     afs
    -0.06
    ÄĽÅ¾
    -0.06
    isine
    -0.06
    hread
    -0.06
    oker
    -0.06
    ipped
    -0.06
    POSITIVE LOGITS
    æį·
    0.08
    thal
    0.07
    fer
    0.07
    pac
    0.07
    fold
    0.07
    ings
    0.06
    ÑĦеÑĢ
    0.06
    ÑĢив
    0.06
    Bloc
    0.06
    yz
    0.06
    Activations Density 0.008%

    No Known Activations