© 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. 69004
    Prev
    Next
    INDEX
    Explanations

    negative constructs and expressions of uncertainty or doubt

    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
    iaz
    -0.07
    TOTYPE
    -0.07
    åĨ
    -0.07
    atu
    -0.07
    enstein
    -0.07
    DEC
    -0.06
    .zh
    -0.06
    _tc
    -0.06
    ologue
    -0.06
    åĹ
    -0.06
    POSITIVE LOGITS
    ĶåĽŀ
    0.08
    ings
    0.07
    å¦ĤæѤ
    0.07
    edly
    0.07
     upon
    0.07
     occasion
    0.07
    unto
    0.07
    oggler
    0.07
    INGS
    0.07
    criptor
    0.07
    Activations Density 0.128%

    No Known Activations