© 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 EvalsExportsinterp-engineNEWAPI 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. 54766
    Prev
    Next
    INDEX
    Explanations

    discussions about software features and compatibility issues

    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
    inem
    -0.07
    zione
    -0.07
    kün
    -0.06
    Your
    -0.06
    uC
    -0.06
    лин
    -0.06
     Your
    -0.06
    agna
    -0.06
    andum
    -0.06
     procedure
    -0.06
    POSITIVE LOGITS
     Heller
    0.07
    .prod
    0.07
    Ŀ
    0.07
    egan
    0.06
    .export
    0.06
    _Group
    0.06
    å°İ
    0.06
     Features
    0.06
    "group
    0.06
    irket
    0.06
    Activations Density 0.001%

    No Known Activations