© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61448
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and terminologies related to biology and chemistry, particularly those involving protein structures and functions

    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
    avana
    -0.07
    uru
    -0.07
    jiang
    -0.06
    at
    -0.06
    _VER
    -0.06
    ubi
    -0.06
     downtown
    -0.06
    vr
    -0.06
    caster
    -0.06
    uard
    -0.05
    POSITIVE LOGITS
    URRENT
    0.07
    á»Ļn
    0.07
     utility
    0.07
    leÅŁik
    0.07
    ropri
    0.07
     desn
    0.07
    Łèĥ½
    0.07
    ê¸°ë¡ľ
    0.07
     capability
    0.07
    suit
    0.07
    Activations Density 0.057%

    No Known Activations