© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84935
    Prev
    Next
    INDEX
    Explanations

    references to document structure and organization

    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
    legen
    -0.06
    ilde
    -0.06
    ording
    -0.06
    loh
    -0.06
    bam
    -0.05
    +
    -0.05
     exact
    -0.05
    thing
    -0.05
    ass
    -0.05
     stall
    -0.05
    POSITIVE LOGITS
     book
    0.09
     report
    0.09
     chapters
    0.09
    report
    0.09
    book
    0.08
    elper
    0.08
     chapter
    0.08
     REPORT
    0.08
     <!--[
    0.08
    chapter
    0.08
    Activations Density 0.027%

    No Known Activations