© 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. 61468
    Prev
    Next
    INDEX
    Explanations

    phrases related to speech and communication

    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
    ivo
    -0.07
    ampil
    -0.06
     Mol
    -0.06
    lauf
    -0.06
    583
    -0.06
    stead
    -0.06
    forth
    -0.06
    cheon
    -0.06
    alc
    -0.06
    ugh
    -0.06
    POSITIVE LOGITS
     things
    0.08
     something
    0.07
    _stuff
    0.07
    stants
    0.07
    ãĥ¼ãĥī
    0.07
    _marshall
    0.07
    aidu
    0.07
     trú
    0.06
    boarding
    0.06
    oque
    0.06
    Activations Density 0.025%

    No Known Activations