© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71269
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotional reactions and disturbances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word fragments that form parts of adjectives expressing negative emotions, frustration, or unpleasant reactions when combined with prefixes/suffixes.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    stral
    -0.08
    uels
    -0.07
    cq
    -0.07
    mps
    -0.07
    imes
    -0.07
    anness
    -0.06
    acb
    -0.06
    uraa
    -0.06
    ewise
    -0.06
    itize
    -0.06
    POSITIVE LOGITS
    ingly
    0.19
    edly
    0.08
    ened
    0.07
    ãĥ¼ãĥĨ
    0.07
    ington
    0.07
    vetica
    0.07
    lectual
    0.07
     intim
    0.07
    ful
    0.07
    ogan
    0.07
    Activations Density 0.030%

    No Known Activations