© 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. 116705
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe actions or characteristics in a negative or ironic context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    achs
    -0.07
    ÅĻ
    -0.07
    isation
    -0.07
    tember
    -0.06
    ing
    -0.06
    ables
    -0.06
    á»ijt
    -0.06
    صب
    -0.06
    ibilities
    -0.06
    елик
    -0.06
    POSITIVE LOGITS
    ly
    0.22
    LY
    0.16
    ically
    0.14
    istically
    0.13
    mente
    0.13
    antly
    0.12
    fully
    0.12
    ely
    0.12
    edly
    0.12
    ously
    0.12
    Activations Density 0.030%

    No Known Activations