© 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. 56109
    Prev
    Next
    INDEX
    Explanations

    function definitions and method calls within programming or code snippets

    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
    .tm
    -0.07
    ÃŃrk
    -0.06
     TypeName
    -0.06
    HasBeenSet
    -0.06
    itty
    -0.06
    #ad
    -0.06
    antine
    -0.06
    propri
    -0.06
    à¸Ńà¸ģ
    -0.06
    agara
    -0.06
    POSITIVE LOGITS
    enheim
    0.07
    metatable
    0.07
    orses
    0.06
    .deepcopy
    0.06
    .advance
    0.06
    urement
    0.06
    çļĦæĺ¯
    0.06
    oir
    0.06
    ÄĻp
    0.06
    kaar
    0.06
    Activations Density 0.036%

    No Known Activations