© 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. 117444
    Prev
    Next
    INDEX
    Explanations

    references to identity and self-identification concepts

    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
    antino
    -0.07
     PROGMEM
    -0.07
    olem
    -0.07
    kazy
    -0.07
     neger
    -0.07
    quires
    -0.07
    Ø°Ùĩ
    -0.07
    Úĺ
    -0.06
    eload
    -0.06
    elim
    -0.06
    POSITIVE LOGITS
     myself
    0.11
     lay
    0.07
     Lay
    0.07
     matter
    0.07
     former
    0.07
    797
    0.06
     someone
    0.06
    Ø´ÙĪ
    0.06
     parents
    0.06
    uras
    0.06
    Activations Density 0.014%

    No Known Activations