© 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. 85968
    Prev
    Next
    INDEX
    Explanations

    emphasizing adverbs and adjectives that indicate intensity

    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
    ibil
    -0.07
    inoa
    -0.07
    OMP
    -0.07
    zyst
    -0.07
    OMIC
    -0.07
    hti
    -0.06
    ansson
    -0.06
    ÑĢÑĥÑĪ
    -0.06
    ega
    -0.06
    ppard
    -0.06
    POSITIVE LOGITS
    fx
    0.07
    iesen
    0.07
    yne
    0.06
    emens
    0.06
    itten
    0.06
    339
    0.06
    isposable
    0.06
    PrototypeOf
    0.05
    ãĥ³ãĤº
    0.05
    longleftrightarrow
    0.05
    Activations Density 0.052%

    No Known Activations