© 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. 94683
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that indicate degrees of change or impact

    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
     slightly
    -0.07
    ght
    -0.07
    _FEATURE
    -0.07
    ke
    -0.06
    KE
    -0.06
     resp
    -0.06
    elay
    -0.06
    endra
    -0.06
     somewhat
    -0.06
    ableViewController
    -0.06
    POSITIVE LOGITS
    yne
    0.07
    igu
    0.07
    tsky
    0.06
    udden
    0.06
     amounts
    0.06
    443
    0.06
    /all
    0.06
     TIMES
    0.06
    mah
    0.06
    è·¡
    0.06
    Activations Density 0.017%

    No Known Activations