© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85268
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to individuals or groups' feelings and 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
    arna
    -0.07
    irit
    -0.07
    Å¡ov
    -0.07
    avax
    -0.07
    vla
    -0.07
    ÃŃrk
    -0.07
    iol
    -0.06
    ÌĨ
    -0.06
    PTY
    -0.06
    esModule
    -0.06
    POSITIVE LOGITS
     chosen
    0.07
    óÅĤ
    0.06
     Goodman
    0.06
    reau
    0.06
    bers
    0.06
     Hut
    0.06
    ictions
    0.06
    uby
    0.06
    ³
    0.06
    erie
    0.06
    Activations Density 0.031%

    No Known Activations