© 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. 72113
    Prev
    Next
    INDEX
    Explanations

    references to events and exhibitions

    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
    oud
    -0.08
    avax
    -0.08
    OMUX
    -0.07
    enschaft
    -0.07
     Gallup
    -0.07
    коÑĤ
    -0.06
    vation
    -0.06
    bid
    -0.06
    оÑģÑĥд
    -0.06
    yclopedia
    -0.06
    POSITIVE LOGITS
    377
    0.06
     conventions
    0.06
    ossa
    0.06
    446
    0.06
     festivals
    0.06
    ãģĵãģ¨ãĤĤ
    0.05
     Olympics
    0.05
    .syntax
    0.05
    raç
    0.05
    -kit
    0.05
    Activations Density 0.034%

    No Known Activations