© 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. 73455
    Prev
    Next
    INDEX
    Explanations

    references to events and actions occurring in a programming context

    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
    aylight
    -0.08
    awe
    -0.08
    æŁIJ
    -0.08
    説
    -0.07
     migrationBuilder
    -0.07
     struk
    -0.07
    alah
    -0.07
    ertino
    -0.07
    @protocol
    -0.07
    είÏĦε
    -0.07
    POSITIVE LOGITS
     we
    0.07
     using
    0.06
    using
    0.06
    zie
    0.06
    hani
    0.06
     courtesy
    0.05
    elli
    0.05
     expression
    0.05
     type
    0.05
    ival
    0.05
    Activations Density 0.026%

    No Known Activations