© 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. 69686
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong enthusiasm or positive feelings

    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
    braco
    -0.08
    emens
    -0.07
    ailles
    -0.06
    erdale
    -0.06
    ei
    -0.06
    lie
    -0.06
    ÃŃsticas
    -0.06
    chet
    -0.06
    ember
    -0.06
    onacci
    -0.06
    POSITIVE LOGITS
     ever
    0.08
     hell
    0.08
     usual
    0.07
    ikal
    0.06
    ieves
    0.06
    sembler
    0.06
     heck
    0.06
     depreci
    0.06
    ldkf
    0.06
    ần
    0.06
    Activations Density 0.015%

    No Known Activations