© 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. 15-LLAMASCOPE-RES-131K
    11. 90752
    Prev
    Next
    INDEX
    Explanations

    references to programming tools and functions related to data manipulation and testing

    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
    oret
    -0.06
    ,
    -0.06
     port
    -0.06
    eme
    -0.06
    ;
    -0.06
    vit
    -0.05
     fertile
    -0.05
    iff
    -0.05
    .
    -0.05
     caus
    -0.05
    POSITIVE LOGITS
    çĽijåIJ¬é¡µéĿ¢
    0.08
     INTERRUPTION
    0.08
    ofile
    0.07
    agas
    0.07
    AlmostEqual
    0.07
    jis
    0.07
     ÑĢеÑģ
    0.07
    ascript
    0.07
    contenido
    0.07
    pedia
    0.07
    Activations Density 0.030%

    No Known Activations