© 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. 17-LLAMASCOPE-RES-131K
    11. 58001
    Prev
    Next
    INDEX
    Explanations

    function definitions and their parameters in code

    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
    -0.06
    utz
    -0.06
     on
    -0.05
     --
    -0.05
    ,
    -0.05
    ael
    -0.05
     sex
    -0.05
    l
    -0.05
    uw
    -0.05
     Conce
    -0.05
    POSITIVE LOGITS
     super
    0.32
    super
    0.28
     Super
    0.25
    (super
    0.25
    Super
    0.23
    	super
    0.23
    .super
    0.23
    _super
    0.23
     SUPER
    0.21
    uper
    0.20
    Activations Density 0.142%

    No Known Activations