© 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. 9-LLAMASCOPE-RES-131K
    11. 94796
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to the self or others

    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
    kö
    -0.07
    .setViewport
    -0.06
    ienia
    -0.06
    rade
    -0.06
    ahat
    -0.06
    åľ³
    -0.06
    istrovstvÃŃ
    -0.06
    ả
    -0.06
     tá»ĭch
    -0.06
    .sz
    -0.06
    POSITIVE LOGITS
    602
    0.07
    olta
    0.07
    олж
    0.07
     provision
    0.06
    Stuff
    0.06
     Lex
    0.06
    ONT
    0.06
     cred
    0.06
    ä¿¡
    0.06
    ANGE
    0.06
    Activations Density 0.003%

    No Known Activations