© 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. 3661
    Prev
    Next
    INDEX
    Explanations

    words related to titles and headings in the document

    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
    arily
    -0.07
    ensch
    -0.07
    zik
    -0.07
     cul
    -0.07
    ekk
    -0.07
    621
    -0.06
    erland
    -0.06
    ritz
    -0.06
    antro
    -0.06
    æ·»
    -0.06
    POSITIVE LOGITS
    =title
    0.08
    _singular
    0.07
    ãĥ³ãĥĩ
    0.07
     Robbins
    0.06
    wargs
    0.06
    /head
    0.06
    -area
    0.06
    -less
    0.06
    arda
    0.06
    orous
    0.06
    Activations Density 0.015%

    No Known Activations