© 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. 79926
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to data privacy and user agreements

    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
     pr
    -0.06
    alted
    -0.06
    retweeted
    -0.06
    amo
    -0.06
    allen
    -0.06
    anta
    -0.06
    hea
    -0.05
    lycer
    -0.05
     discriminate
    -0.05
    طة
    -0.05
    POSITIVE LOGITS
    اÙħÙĩ
    0.08
    ë°°
    0.08
    ã
    0.07
    bette
    0.07
    .cons
    0.07
    ãģ¡ãģ¯
    0.07
    åļ
    0.07
    aldo
    0.07
    (Convert
    0.07
    ogenerated
    0.07
    Activations Density 0.003%

    No Known Activations