© 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. 125652
    Prev
    Next
    INDEX
    Explanations

    file handling and file manipulation operations 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
    immel
    -0.07
    culos
    -0.06
    erno
    -0.06
    ead
    -0.06
    ilege
    -0.06
    FieldType
    -0.06
    æݨ
    -0.06
    onu
    -0.06
    ÃŃsk
    -0.06
    rana
    -0.06
    POSITIVE LOGITS
    okit
    0.07
    creativecommons
    0.06
     Jennings
    0.06
     eff
    0.06
     Bare
    0.06
    _managed
    0.06
    etAddress
    0.06
    ?>>
    0.05
    GLISH
    0.05
    clientes
    0.05
    Activations Density 0.008%

    No Known Activations