© 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. 118195
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating existence or action

    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
    ikip
    -0.07
    ếu
    -0.07
    ablo
    -0.07
    egal
    -0.07
    _defs
    -0.06
    gratis
    -0.06
    ICODE
    -0.06
    ÑĢÑĥÑģ
    -0.06
    ICAST
    -0.06
    EIF
    -0.06
    POSITIVE LOGITS
    eme
    0.07
     Underground
    0.07
    ona
    0.07
     nevertheless
    0.06
    isha
    0.06
    ime
    0.06
     automáticamente
    0.06
    ãģ¡ãĤĥ
    0.06
    aze
    0.06
    ĵĺ
    0.06
    Activations Density 0.015%

    No Known Activations