© 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. 9-LLAMASCOPE-RES-131K
    11. 96872
    Prev
    Next
    INDEX
    Explanations

    references to programming and entity models

    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
    zie
    -0.07
    webdriver
    -0.07
    lsen
    -0.07
    MBER
    -0.07
    uin
    -0.07
    heid
    -0.07
    ĺ认
    -0.07
    igest
    -0.07
     件
    -0.07
    jing
    -0.06
    POSITIVE LOGITS
     Mans
    0.07
    mans
    0.06
    rava
    0.06
     eventual
    0.06
    é¡į
    0.05
    ultipartFile
    0.05
     Genius
    0.05
    cro
    0.05
     having
    0.05
    ael
    0.05
    Activations Density 0.003%

    No Known Activations