© 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. 73882
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to people

    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
    /Instruction
    -0.09
    annes
    -0.07
    rlen
    -0.07
    oklyn
    -0.07
    اختÙĩ
    -0.07
    йн
    -0.07
    ustin
    -0.07
    unga
    -0.07
    strup
    -0.07
    pte
    -0.07
    POSITIVE LOGITS
    ç»ĻæĪij
    0.08
    addtogroup
    0.06
     Wheeler
    0.06
     mine
    0.06
     my
    0.06
    让æĪij
    0.06
    λÏī
    0.06
     seemed
    0.06
     Apost
    0.06
     mir
    0.06
    Activations Density 0.052%

    No Known Activations