© 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. 92963
    Prev
    Next
    INDEX
    Explanations

    expressions of strong admiration and emotional connection to a specific television show and its related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    User-generated content expressing personal experiences, opinions, and informal conversation, typically from social media, forums, or blog-style writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     folks
    -0.07
     fung
    -0.06
    ugen
    -0.06
     Ive
    -0.06
     ==>
    -0.06
    arpa
    -0.06
     early
    -0.06
    ivec
    -0.06
     vertical
    -0.06
     additional
    -0.06
    POSITIVE LOGITS
    !!!!!!!!
    0.07
    roe
    0.07
    inet
    0.07
    _instr
    0.07
     retal
    0.07
    wich
    0.07
    omas
    0.07
    jee
    0.06
     Buen
    0.06
    stuff
    0.06
    Activations Density 0.636%

    No Known Activations