© 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. 106610
    Prev
    Next
    INDEX
    Explanations

    mentions of food and dining experiences

    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
    ekim
    -0.09
    erece
    -0.08
     Fucking
    -0.08
    ivant
    -0.08
    ustos
    -0.08
    icari
    -0.08
     fucking
    -0.08
     FUCK
    -0.08
    ercial
    -0.08
    umo
    -0.07
    POSITIVE LOGITS
     puff
    0.06
    gov
    0.06
     Rug
    0.06
     combos
    0.06
     Aura
    0.06
     Termin
    0.05
     Confeder
    0.05
     Aber
    0.05
    orb
    0.05
    -datepicker
    0.05
    Activations Density 0.000%

    No Known Activations