© 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. 73291
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "throw" and its variations

    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
    arily
    -0.08
    ials
    -0.07
    ummings
    -0.06
    ienda
    -0.06
    ηÏĤ
    -0.06
    ually
    -0.06
    .au
    -0.06
    iable
    -0.06
    irm
    -0.06
    ÑĤÑİ
    -0.06
    POSITIVE LOGITS
    abouts
    0.10
    away
    0.10
    aways
    0.09
    .Tasks
    0.08
    back
    0.08
    backs
    0.07
     lẫn
    0.07
    throw
    0.07
    SPORT
    0.07
    izzy
    0.07
    Activations Density 0.015%

    No Known Activations