© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 96134
    Prev
    Next
    INDEX
    Explanations

    variations of the word "custom."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    еннÑı
    -0.07
    	↵
    -0.07
    ISM
    -0.07
    contres
    -0.07
    isoft
    -0.07
    asure
    -0.07
    onna
    -0.06
    _sdk
    -0.06
    ROP
    -0.06
    KT
    -0.06
    POSITIVE LOGITS
    arily
    0.13
    izing
    0.12
    isable
    0.11
    izations
    0.11
    ised
    0.11
    ized
    0.10
    izable
    0.10
    mers
    0.10
    -made
    0.10
    -built
    0.09
    Activations Density 0.010%

    No Known Activations