© 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. 77116
    Prev
    Next
    INDEX
    Explanations

    references to scientific data and measurements

    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
    idge
    -0.06
    abus
    -0.06
     localhost
    -0.06
    presso
    -0.06
     ethics
    -0.06
    erse
    -0.06
     swell
    -0.06
     vol
    -0.05
     Establishment
    -0.05
    clare
    -0.05
    POSITIVE LOGITS
    UBE
    0.07
    JsonValue
    0.07
    ãĥ¬ãĥ³
    0.07
    ála
    0.07
    _RT
    0.07
     TOD
    0.07
    èŀ
    0.07
    èĤī
    0.07
     keyed
    0.07
    ube
    0.07
    Activations Density 0.029%

    No Known Activations