© 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. 59021
    Prev
    Next
    INDEX
    Explanations

    expressions related to conveying feelings and emotions

    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
    Enlarge
    -0.07
    ies
    -0.07
    assis
    -0.06
    pron
    -0.06
    ÑģпÑĸлÑĮ
    -0.06
    REFER
    -0.06
    unker
    -0.06
    õ
    -0.06
    aring
    -0.06
    baz
    -0.06
    POSITIVE LOGITS
     how
    0.08
    ãĥĥãĥĦ
    0.08
     adequately
    0.07
     suffice
    0.07
     adequ
    0.07
     setDescription
    0.07
     inade
    0.07
    oti
    0.06
     description
    0.06
    unts
    0.06
    Activations Density 0.008%

    No Known Activations