© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60310
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

    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
    entifier
    -0.06
    @brief
    -0.06
    νομ
    -0.06
    ssf
    -0.06
    лÑıв
    -0.06
    clc
    -0.06
    .mongodb
    -0.06
     Robinson
    -0.06
    imli
    -0.06
    duct
    -0.06
    POSITIVE LOGITS
    311
    0.07
    ahr
    0.07
    391
    0.07
    acci
    0.07
    373
    0.06
    over
    0.06
    ZD
    0.06
    otal
    0.06
    rous
    0.06
    100
    0.06
    Activations Density 0.001%

    No Known Activations