© 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. 95509
    Prev
    Next
    INDEX
    Explanations

    vertical bars or dividers in text

    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
    å¡
    -0.07
    zym
    -0.07
    noinspection
    -0.07
    iele
    -0.06
    mani
    -0.06
    acks
    -0.06
    ceans
    -0.06
    otts
    -0.06
    isson
    -0.06
    ears
    -0.06
    POSITIVE LOGITS
    ecom
    0.07
    addock
    0.07
    #
    0.06
    _IDX
    0.06
    aos
    0.06
     batt
    0.06
     Twe
    0.06
     Pager
    0.06
    ILITY
    0.06
    mlink
    0.06
    Activations Density 0.001%

    No Known Activations