© 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. 79934
    Prev
    Next
    INDEX
    Explanations

    references to hate and related negative sentiments

    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
    naire
    -0.09
    дина
    -0.09
    mente
    -0.08
    rei
    -0.08
    gether
    -0.08
    .ManyToMany
    -0.08
    ette
    -0.08
    Ø©
    -0.08
    ÃŁe
    -0.07
    naires
    -0.07
    POSITIVE LOGITS
    fully
    0.08
    fulness
    0.08
     ÙĪرز
    0.07
    full
    0.06
    oley
    0.06
     Bri
    0.06
    endra
    0.06
     McK
    0.06
    flix
    0.06
    ARP
    0.06
    Activations Density 0.003%

    No Known Activations