© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89386
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to business operations and legal structures

    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
     caval
    -0.06
    جد
    -0.06
    ÑĮко
    -0.06
    mpi
    -0.06
     serious
    -0.06
    kit
    -0.06
    hip
    -0.06
     Tubes
    -0.06
    ìŬ
    -0.06
     subj
    -0.06
    POSITIVE LOGITS
     already
    0.08
    already
    0.08
    indle
    0.07
     negligible
    0.07
    elt
    0.06
    _already
    0.06
    obody
    0.06
    ODY
    0.06
    ÑĥÑģÑĤи
    0.06
    Already
    0.06
    Activations Density 0.049%

    No Known Activations