© 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. 40362
    Prev
    Next
    INDEX
    Explanations

    U.S. related content and numerical data

    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
     Grove
    -0.07
    ente
    -0.07
    (include
    -0.06
    æk
    -0.06
    aim
    -0.06
    æ¢
    -0.06
    olic
    -0.06
    gage
    -0.06
    .RunWith
    -0.06
    ecom
    -0.06
    POSITIVE LOGITS
    stal
    0.07
    uste
    0.07
    criptor
    0.07
    _HERSHEY
    0.07
    bau
    0.06
    wig
    0.06
    nika
    0.06
    ampie
    0.06
     Gener
    0.06
     Sunder
    0.06
    Activations Density 0.001%

    No Known Activations