© 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. 15-LLAMASCOPE-RES-131K
    11. 88092
    Prev
    Next
    INDEX
    Explanations

    references to CEO transitions and corporate leadership changes

    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
    ayer
    -0.06
    SSERT
    -0.06
    thal
    -0.06
     bankrupt
    -0.06
    ieren
    -0.06
    kn
    -0.06
    quet
    -0.06
    yer
    -0.06
     deserted
    -0.06
    Synopsis
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.07
    acro
    0.07
    .Undef
    0.07
    ensi
    0.07
    fte
    0.07
    trys
    0.07
    θο
    0.07
     ëĭ¤ìļ´ë°Ľê¸°
    0.07
     replacements
    0.07
    860
    0.06
    Activations Density 0.010%

    No Known Activations