© 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. 15-LLAMASCOPE-RES-131K
    11. 87188
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns indicating personal experiences or reflections

    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
    tal
    -0.06
    antha
    -0.06
    itä
    -0.06
    ÅĤaw
    -0.06
    eward
    -0.06
    edicine
    -0.06
    ponible
    -0.06
    ije
    -0.06
    ipp
    -0.06
     Err
    -0.06
    POSITIVE LOGITS
     agree
    0.07
    also
    0.07
    mayan
    0.07
     Agree
    0.07
     also
    0.07
    chio
    0.06
    Also
    0.06
    ìĿ´ìĸ´
    0.06
     recently
    0.06
     Also
    0.06
    Activations Density 0.039%

    No Known Activations