© 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. 93844
    Prev
    Next
    INDEX
    Explanations

    emotional and psychological states related to performance or outcomes

    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
    oined
    -0.09
    adesh
    -0.08
    ambi
    -0.07
     amac
    -0.07
    atoria
    -0.07
    udson
    -0.07
    edik
    -0.07
    atchet
    -0.07
    asant
    -0.07
    icaid
    -0.06
    POSITIVE LOGITS
     advantage
    0.08
     effect
    0.08
     Advantage
    0.08
     disadvantage
    0.07
     affect
    0.07
    illy
    0.07
     advantages
    0.07
     effects
    0.07
     affects
    0.06
    .extent
    0.06
    Activations Density 0.027%

    No Known Activations