© 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. 15505
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and colons

    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
    iddet
    -0.08
    ICAST
    -0.06
    èİ
    -0.06
    .MixedReality
    -0.06
    aland
    -0.06
    énom
    -0.06
    untime
    -0.06
    vais
    -0.06
    ÅĽci
    -0.06
    raries
    -0.06
    POSITIVE LOGITS
    ANNEL
    0.08
    odef
    0.07
     Eudicots
    0.07
    ipers
    0.06
    595
    0.06
    ankind
    0.06
    erras
    0.06
     dab
    0.06
    اÙģظ
    0.06
    699
    0.06
    Activations Density 0.001%

    No Known Activations