© 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. 96643
    Prev
    Next
    INDEX
    Explanations

    formatted code or script elements and comments

    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
    TRACE
    -0.07
    yth
    -0.07
    doch
    -0.07
     Astros
    -0.07
    ServerError
    -0.06
    sg
    -0.06
    Trace
    -0.06
    ëĭµ
    -0.06
    752
    -0.06
     ogl
    -0.06
    POSITIVE LOGITS
     camb
    0.09
    lish
    0.07
    ailer
    0.06
    eton
    0.06
    rello
    0.06
    oho
    0.06
    isky
    0.06
    isl
    0.06
    olin
    0.06
     Summer
    0.06
    Activations Density 0.001%

    No Known Activations