© 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. 92912
    Prev
    Next
    INDEX
    Explanations

    sentences ending with punctuation or significant transitional expressions

    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
    odia
    -0.06
    attach
    -0.06
    ://
    -0.06
     bless
    -0.06
    ask
    -0.06
    eng
    -0.06
    ean
    -0.06
     via
    -0.05
    :
    -0.05
    )-(
    -0.05
    POSITIVE LOGITS
    ↵↵
    0.09
    warts
    0.08
     onRequest
    0.07
    deniz
    0.07
    DataMember
    0.07
    /cms
    0.07
    Lets
    0.07
    ToFit
    0.07
    DBObject
    0.07
    oggle
    0.07
    Activations Density 0.034%

    No Known Activations