© 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 EvalsExportsAPI 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. 106648
    Prev
    Next
    INDEX
    Explanations

    parentheses and numerical values

    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
    strup
    -0.07
    azor
    -0.06
     Fridays
    -0.06
    arent
    -0.06
    azed
    -0.06
    rous
    -0.06
    .gwt
    -0.06
     Cursors
    -0.06
    adoras
    -0.06
    ooky
    -0.06
    POSITIVE LOGITS
    ilo
    0.08
    :normal
    0.07
    unca
    0.07
    ÙĦÙĬÙĦ
    0.07
    buz
    0.07
    Zone
    0.06
    éĹ
    0.06
    agini
    0.06
    رÙĬاض
    0.06
    isd
    0.06
    Activations Density 0.000%

    No Known Activations