© 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. 83780
    Prev
    Next
    INDEX
    Explanations

    names of authors and their affiliations in academic publications

    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
    eprom
    -0.07
    isque
    -0.07
    inel
    -0.06
    ubber
    -0.06
    amarin
    -0.06
    erts
    -0.06
     é¹
    -0.06
    reator
    -0.06
    drv
    -0.06
    ectar
    -0.06
    POSITIVE LOGITS
    elf
    0.07
    ajan
    0.07
    IVEN
    0.06
    ÑģÑĮ
    0.06
    unk
    0.06
    âĢı
    0.06
    inox
    0.06
    licht
    0.06
     actively
    0.06
    ема
    0.06
    Activations Density 0.001%

    No Known Activations