© 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 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. 16346
    Prev
    Next
    INDEX
    Explanations

    instances of structured formatting and layout descriptions

    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
    ?url
    -0.06
    лаÑĤÑĥ
    -0.06
    βάλ
    -0.06
    .spin
    -0.06
    ãģ¨ãģĨ
    -0.05
    lim
    -0.05
    enzhen
    -0.05
    icz
    -0.05
    CEPT
    -0.05
    pare
    -0.05
    POSITIVE LOGITS
    \:
    0.07
    #ac
    0.07
    aines
    0.07
    Uvs
    0.06
    lopedia
    0.06
    owered
    0.06
    ัà¸ļสà¸Ļ
    0.06
    Radians
    0.06
    åħ¥ãĤĬ
    0.06
     MetroFramework
    0.06
    Activations Density 0.013%

    No Known Activations