© 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. 73823
    Prev
    Next
    INDEX
    Explanations

    expressions of positive emotional sentiments or affection

    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
    lette
    -0.07
    TRA
    -0.07
     çµIJ
    -0.07
    GLE
    -0.07
    lue
    -0.07
    hl
    -0.06
    lex
    -0.06
    UMAN
    -0.06
    itzer
    -0.06
    ÑĢив
    -0.06
    POSITIVE LOGITS
    isel
    0.07
    ays
    0.07
    TING
    0.06
    LANG
    0.06
    ching
    0.06
    unes
    0.06
    ELY
    0.06
    _subtitle
    0.06
    elyn
    0.06
    iner
    0.06
    Activations Density 0.006%

    No Known Activations