© 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. 17-LLAMASCOPE-RES-131K
    11. 129925
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly by name

    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
    achuset
    -0.10
    pa
    -0.10
    pu
    -0.08
    entin
    -0.08
    oftware
    -0.08
    ma
    -0.08
    au
    -0.08
    li
    -0.08
    a
    -0.08
    men
    -0.08
    POSITIVE LOGITS
    ê¹
    0.10
    zelf
    0.09
    ến
    0.08
    ÅĽmy
    0.08
    uations
    0.08
    á»ģn
    0.07
    erra
    0.07
    oux
    0.07
    LOT
    0.07
    -fw
    0.07
    Activations Density 0.059%

    No Known Activations