© 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. 83299
    Prev
    Next
    INDEX
    Explanations

    references to publishing and creative works

    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
    apon
    -0.07
    κε
    -0.07
    coal
    -0.06
     manually
    -0.06
    mirror
    -0.06
    allet
    -0.06
    DS
    -0.06
    966
    -0.06
    AF
    -0.06
    required
    -0.06
    POSITIVE LOGITS
     submitting
    0.07
     debut
    0.06
    éŁ
    0.06
     ÑĤов
    0.06
     publi
    0.06
     âĹİ
    0.06
     placement
    0.06
    /***/
    0.06
    Pane
    0.06
     placements
    0.06
    Activations Density 0.068%

    No Known Activations