© 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. 62373
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminologies related to equilibrium shapes in various configurations

    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
    vio
    -0.08
    andbox
    -0.08
    cratch
    -0.07
     ChÃŃ
    -0.07
    thought
    -0.07
    vla
    -0.07
    ovu
    -0.07
    è»
    -0.07
    åĪĬ
    -0.07
    bote
    -0.07
    POSITIVE LOGITS
    chk
    0.07
     Spinner
    0.06
     Gast
    0.06
     Laure
    0.06
     Walters
    0.06
     Pare
    0.06
     Held
    0.05
     Ñĥв
    0.05
    ammen
    0.05
     Gloss
    0.05
    Activations Density 0.008%

    No Known Activations