© 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. 30527
    Prev
    Next
    INDEX
    Explanations

    Swedish language characters and various forms of the word "samhälle," indicating a focus on societal concepts

    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
    akov
    -0.08
    ogh
    -0.08
    otty
    -0.07
    xdb
    -0.07
    iosa
    -0.06
    _AST
    -0.06
    bread
    -0.06
    çĸĨ
    -0.06
    bir
    -0.06
    inish
    -0.06
    POSITIVE LOGITS
    erville
    0.06
    ronic
    0.06
    801
    0.06
    enet
    0.06
    spot
    0.06
     Joel
    0.06
    sville
    0.06
     ê³³
    0.06
    åĭ¢
    0.06
    ORIZONTAL
    0.06
    Activations Density 0.001%

    No Known Activations