© 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. 15-LLAMASCOPE-RES-131K
    11. 86709
    Prev
    Next
    INDEX
    Explanations

    expressions of taste and desirability in food descriptions

    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
    MUX
    -0.06
    orra
    -0.06
    ppers
    -0.06
     IPPROTO
    -0.06
    exas
    -0.06
    dating
    -0.06
     frosting
    -0.06
     Düz
    -0.06
    ir
    -0.06
    bak
    -0.05
    POSITIVE LOGITS
    ุส
    0.07
    Ľi
    0.07
    adden
    0.06
     addictive
    0.06
     Homes
    0.06
     addict
    0.06
     Layers
    0.06
    جار
    0.06
    ôm
    0.06
    umpt
    0.06
    Activations Density 0.015%

    No Known Activations