© 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. 92933
    Prev
    Next
    INDEX
    Explanations

    variations of the word "gener" and associated terms

    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
    OTE
    -0.07
    ation
    -0.07
    grim
    -0.06
    cz
    -0.06
    Ø©
    -0.06
    celik
    -0.06
     judgment
    -0.06
    cut
    -0.06
    shore
    -0.06
    glomer
    -0.06
    POSITIVE LOGITS
    ational
    0.08
    -LAST
    0.08
    tru
    0.07
    ius
    0.07
    hea
    0.07
    osa
    0.07
    -gap
    0.07
    ERIC
    0.07
    .Generation
    0.06
    ators
    0.06
    Activations Density 0.007%

    No Known Activations