© 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. 108105
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Boo Seeka."

    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
    esini
    -0.07
    urus
    -0.06
     Bale
    -0.06
    iesel
    -0.06
    alama
    -0.06
    æ¨
    -0.06
     Overs
    -0.06
    ovan
    -0.06
    bol
    -0.06
     INCLUDE
    -0.06
    POSITIVE LOGITS
     Rank
    0.06
    linkplain
    0.06
    ]âĢı
    0.06
    ursal
    0.06
     {{--<
    0.06
     Throne
    0.06
    ÏĢη
    0.06
    ноÑģ
    0.06
     Lung
    0.06
    gow
    0.06
    Activations Density 0.000%

    No Known Activations