© 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. 82030
    Prev
    Next
    INDEX
    Explanations

    phrases related to dating, registration, and participation criteria in online platforms

    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
    Ñħов
    -0.07
    ÙĨب
    -0.07
    borg
    -0.07
    otland
    -0.07
     rub
    -0.07
    ccak
    -0.06
     PROGMEM
    -0.06
    ĶåĽŀ
    -0.06
     CircularProgress
    -0.06
    creativecommons
    -0.06
    POSITIVE LOGITS
    üz
    0.06
    ac
    0.06
    ogg
    0.06
    èħ°
    0.06
    125
    0.06
     MSM
    0.06
    agues
    0.06
    óz
    0.06
    ãĤħ
    0.06
    aml
    0.06
    Activations Density 0.001%

    No Known Activations