© 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. 57383
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to educational institutions and scientific fields

    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
    ORMAL
    -0.06
     (
    -0.06
    TestMethod
    -0.06
    ÐĹап
    -0.06
    otine
    -0.06
    joy
    -0.06
    ãħĭãħĭãħĭãħĭ
    -0.06
    jac
    -0.06
    abor
    -0.05
    egers
    -0.05
    POSITIVE LOGITS
    /Foundation
    0.07
    ijkl
    0.06
    <\/
    0.06
    ewis
    0.06
    imed
    0.06
    /WebAPI
    0.06
    бÑĥ
    0.06
    ↵
    0.06
    elerini
    0.06
    θεν
    0.06
    Activations Density 0.025%

    No Known Activations