© 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. 6007
    Prev
    Next
    INDEX
    Explanations

    words that express uncertainty or probability

    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
    ::*
    -0.07
    umbn
    -0.07
    åıĬãģ³
    -0.06
    _tF
    -0.06
    \_
    -0.06
    aat
    -0.06
    arius
    -0.06
    hub
    -0.06
    izza
    -0.06
     ознаÑĩа
    -0.06
    POSITIVE LOGITS
     be
    0.15
     been
    0.10
    most
    0.09
    forth
    0.08
    ãĤ·ãĥ¼
    0.07
    iam
    0.07
     have
    0.07
    umo
    0.07
    awa
    0.07
    ï¸ı
    0.07
    Activations Density 0.099%

    No Known Activations