© 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. 117343
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of self and emotion

    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
    ableViewController
    -0.08
    orca
    -0.08
    ãģ®ãģł
    -0.08
    nore
    -0.07
    è
    -0.07
    ercul
    -0.07
    ancellor
    -0.07
    лаб
    -0.07
    aps
    -0.07
    typeid
    -0.07
    POSITIVE LOGITS
     Andr
    0.06
    izer
    0.06
     mean
    0.06
     think
    0.06
     saying
    0.05
     [
    0.05
     Saw
    0.05
     just
    0.05
     borders
    0.05
     palp
    0.05
    Activations Density 0.047%

    No Known Activations