© 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. 15275
    Prev
    Next
    INDEX
    Explanations

    themes related to personal and social identity, secrets, and the act of revealing knowledge or experiences

    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
     ná»ķi
    -0.07
    ÑĢап
    -0.07
    pai
    -0.07
     Verfüg
    -0.07
    دÙĩ
    -0.07
     ë§IJìĿ´
    -0.06
     пÑĢопози
    -0.06
    áp
    -0.06
    رد
    -0.06
    zeÅĦ
    -0.06
    POSITIVE LOGITS
     hidden
    0.12
     secrets
    0.12
     details
    0.10
     Secrets
    0.09
     underlying
    0.09
    éļIJèĹı
    0.09
     hiding
    0.09
     Hidden
    0.09
    hidden
    0.08
     truth
    0.08
    Activations Density 0.034%

    No Known Activations