© 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. 69219
    Prev
    Next
    INDEX
    Explanations

    different forms of the verb "speak" and its related actions

    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
    ruz
    -0.08
    rek
    -0.07
    esel
    -0.07
    rupa
    -0.07
     Mitar
    -0.07
    rana
    -0.07
    icz
    -0.07
    bih
    -0.07
    icari
    -0.07
     smrt
    -0.07
    POSITIVE LOGITS
    ³
    0.06
    Sense
    0.06
     Rim
    0.06
     Hin
    0.06
    .CodeAnalysis
    0.06
    ξι
    0.06
     Rif
    0.06
    ίκ
    0.06
    omba
    0.06
     about
    0.05
    Activations Density 0.012%

    No Known Activations