© 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. 41313
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness and positivity

    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
    amm
    -0.07
    ео
    -0.07
    variants
    -0.07
     ẩn
    -0.06
    arrow
    -0.06
    ideon
    -0.06
    åIJįåīį
    -0.06
     Variant
    -0.06
    ê°Ŀ
    -0.06
    ECH
    -0.06
    POSITIVE LOGITS
    -go
    0.10
     happy
    0.07
     Happy
    0.07
     HAPP
    0.07
    happy
    0.07
     accidents
    0.07
     endings
    0.07
     Happ
    0.07
    /content
    0.06
    Happy
    0.06
    Activations Density 0.017%

    No Known Activations