© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104024
    Prev
    Next
    INDEX
    Explanations

    terms related to responses and replies in conversations or interactive contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    živ
    -0.07
    imd
    -0.07
    CTSTR
    -0.06
    κÏģι
    -0.06
    _TestCase
    -0.06
    ongan
    -0.06
    lava
    -0.06
    .SDK
    -0.06
    REFIX
    -0.06
    underscore
    -0.06
    POSITIVE LOGITS
    ymbol
    0.07
    inct
    0.06
    fw
    0.06
    mlin
    0.06
    .TypeOf
    0.06
    ugg
    0.06
    utsch
    0.06
    arem
    0.06
    uger
    0.06
    ecided
    0.06
    Activations Density 0.002%

    No Known Activations