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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3261
    Prev
    Next
    INDEX
    Explanations

    intensifiers or modifiers emphasizing the degree of an adjective or adverb

    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
    -0.07
    ávÄĽ
    -0.07
    eya
    -0.07
    تب
    -0.06
    LESS
    -0.06
    ÙħارÛĮ
    -0.06
    osa
    -0.06
    raz
    -0.06
    rescia
    -0.06
     eyewitness
    -0.06
    POSITIVE LOGITS
     nice
    0.07
    orry
    0.07
    ucher
    0.07
     important
    0.07
    erged
    0.06
    /ext
    0.06
     good
    0.06
    Porno
    0.06
    peater
    0.06
    yy
    0.06
    Activations Density 0.016%

    No Known Activations