© 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. 124990
    Prev
    Next
    INDEX
    Explanations

    geographic locations or places

    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
    azzi
    -0.10
    $MESS
    -0.07
    znik
    -0.07
     xOffset
    -0.07
    iki
    -0.07
    inz
    -0.07
    ìĻ¸
    -0.06
    .DAL
    -0.06
    uria
    -0.06
    tÃŃ
    -0.06
    POSITIVE LOGITS
    ,is
    0.07
    arness
    0.07
    ellig
    0.07
    mint
    0.06
    eter
    0.06
     elig
    0.06
    ,to
    0.06
    weit
    0.06
    ël
    0.06
    âĢ³
    0.06
    Activations Density 0.144%

    No Known Activations