© 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. 22-LLAMASCOPE-RES-131K
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    references to copyright information

    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
    acin
    -0.07
    uru
    -0.06
    cin
    -0.06
    runner
    -0.06
     Termin
    -0.06
     bench
    -0.06
    utzer
    -0.06
    usher
    -0.06
     багаÑĤ
    -0.06
    dens
    -0.06
    POSITIVE LOGITS
    grily
    0.07
    readcr
    0.07
    elden
    0.07
    æ®Ĭ
    0.06
    ŀĭ
    0.06
     onAnimation
    0.06
    aju
    0.06
    ÅĽmy
    0.06
    ulen
    0.06
    ersist
    0.06
    Activations Density 0.001%

    No Known Activations