© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124924
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives that convey strong emotional states or reactions

    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
    -0.09
    zan
    -0.08
    ypse
    -0.07
    isle
    -0.07
    tings
    -0.07
    suz
    -0.07
    /Area
    -0.07
    á»Ļc
    -0.07
    ullan
    -0.06
     fittings
    -0.06
    POSITIVE LOGITS
    ly
    0.20
    LY
    0.12
    ÑģÑı
    0.09
    lys
    0.09
    ness
    0.09
    redients
    0.08
    gg
    0.08
    hausen
    0.08
    redient
    0.08
    REDIENT
    0.08
    Activations Density 0.073%

    No Known Activations