© 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. 82827
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "grim" or its variations in the context of negative situations

    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
    aurus
    -0.08
    _CLIP
    -0.07
    elian
    -0.07
    oun
    -0.07
    asurer
    -0.07
    ียà¸ļ
    -0.07
    esis
    -0.06
    ylko
    -0.06
    roll
    -0.06
    use
    -0.06
    POSITIVE LOGITS
    linger
    0.08
    ness
    0.08
    elda
    0.08
    dest
    0.07
    aces
    0.07
    eton
    0.07
    acing
    0.07
    ities
    0.07
    lich
    0.06
    shaw
    0.06
    Activations Density 0.005%

    No Known Activations