© 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. 56095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "respect" in various contexts

    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
    hi
    -0.06
    ffects
    -0.06
    ergic
    -0.06
    iá»ģn
    -0.06
    TERM
    -0.06
    igel
    -0.06
    .DropTable
    -0.06
    anic
    -0.06
    x
    -0.06
    ÑĸлÑĸ
    -0.06
    POSITIVE LOGITS
    lying
    0.07
    antar
    0.07
    LY
    0.06
     Axe
    0.06
    ieve
    0.06
    och
    0.06
    ottom
    0.06
    usan
    0.06
    997
    0.06
     Dickinson
    0.06
    Activations Density 0.007%

    No Known Activations