© 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. 56232
    Prev
    Next
    INDEX
    Explanations

    words related to emotions or descriptors of feelings

    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
    NAMESPACE
    -0.08
    ¾
    -0.07
    ÄIJT
    -0.07
    ennon
    -0.07
    yb
    -0.07
    iya
    -0.07
    æŁ±
    -0.07
    oras
    -0.06
    бÑĭ
    -0.06
    antz
    -0.06
    POSITIVE LOGITS
    developer
    0.06
    venience
    0.06
    sel
    0.06
    linger
    0.06
    endor
    0.06
    ipple
    0.06
    orsk
    0.06
    erna
    0.06
    elon
    0.06
    CI
    0.06
    Activations Density 0.011%

    No Known Activations