© 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. 42761
    Prev
    Next
    INDEX
    Explanations

    adjectives that denote positive attributes or commendation

    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
    ed
    -0.10
    edb
    -0.10
    edBy
    -0.08
    ing
    -0.08
    el
    -0.07
    aro
    -0.07
    ÏĮδ
    -0.07
     sple
    -0.07
    entially
    -0.07
    637
    -0.06
    POSITIVE LOGITS
    mente
    0.09
    NESS
    0.08
    -looking
    0.08
    lest
    0.07
    les
    0.07
    ilty
    0.07
    avage
    0.07
    axter
    0.07
    iores
    0.07
    abant
    0.06
    Activations Density 0.006%

    No Known Activations