© 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. 55116
    Prev
    Next
    INDEX
    Explanations

    programming function invocation and usage

    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
    linger
    -0.07
    è¿
    -0.07
    ermo
    -0.07
    .Padding
    -0.07
    оÑĩка
    -0.07
    оÑĩки
    -0.07
    .terminate
    -0.06
    venting
    -0.06
    umbo
    -0.06
    745
    -0.06
    POSITIVE LOGITS
    ncy
    0.07
    .scalablytyped
    0.06
    eeper
    0.06
     Sav
    0.06
    -scalable
    0.06
    езÑĥлÑĮÑĤ
    0.06
     struck
    0.06
     engaging
    0.06
     overhe
    0.06
    azzi
    0.06
    Activations Density 0.000%

    No Known Activations