© 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 EvalsExportsinterp-engineNEWAPI 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. 1799
    Prev
    Next
    INDEX
    Explanations

    terms associated with unattractiveness or unpleasantness

    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
    ero
    -0.08
    illon
    -0.08
    hoff
    -0.07
    acles
    -0.07
    yles
    -0.06
    lage
    -0.06
    yor
    -0.06
    ISMATCH
    -0.06
    ilion
    -0.06
    ultimate
    -0.06
    POSITIVE LOGITS
    lest
    0.07
    gram
    0.07
     duck
    0.07
     truth
    0.07
    vais
    0.06
    æŁĵ
    0.06
    ADATA
    0.06
    *)"
    0.06
    laması
    0.06
    furt
    0.06
    Activations Density 0.004%

    No Known Activations