© 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. 72179
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Timothy."

    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
    ará
    -0.07
    خش
    -0.07
    poi
    -0.07
    537
    -0.06
    ÙģØ´
    -0.06
    ر
    -0.06
    رÙĤ
    -0.06
    744
    -0.06
    pad
    -0.06
    ãĢħ
    -0.06
    POSITIVE LOGITS
    bred
    0.08
    orus
    0.07
    onth
    0.07
    aki
    0.07
    itus
    0.07
    ivan
    0.07
    ause
    0.07
    unction
    0.07
    orous
    0.06
    aupt
    0.06
    Activations Density 0.003%

    No Known Activations