© 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. 18530
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific types of formatting or symbols

    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
    _MACHINE
    -0.06
    nement
    -0.06
    arent
    -0.06
    ovo
    -0.06
    msp
    -0.06
    меÑĩ
    -0.06
    digits
    -0.06
    sects
    -0.06
    quisar
    -0.06
    duit
    -0.06
    POSITIVE LOGITS
    ords
    0.07
    eken
    0.06
    ipi
    0.06
     Jew
    0.06
     Colony
    0.06
    asel
    0.06
    inz
    0.06
    otor
    0.06
    rou
    0.06
    iken
    0.06
    Activations Density 0.007%

    No Known Activations