© 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. 80977
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to varied emotional states or expressions

    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
    emens
    -0.08
    ÑģÑĤав
    -0.07
    itre
    -0.07
    openh
    -0.07
     unin
    -0.07
    utsch
    -0.07
     sert
    -0.07
    ppard
    -0.07
    нина
    -0.07
     Nová
    -0.07
    POSITIVE LOGITS
    yd
    0.08
     factor
    0.07
    itzer
    0.07
    ching
    0.06
    ington
    0.06
    lete
    0.06
    iness
    0.06
     Hew
    0.06
    factor
    0.06
    ingly
    0.06
    Activations Density 0.067%

    No Known Activations