Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96091
    Prev
    Next
    INDEX
    Explanations

    references and citations in a 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
    atar
    -0.07
    oulouse
    -0.06
    rena
    -0.06
    colo
    -0.06
    iale
    -0.05
    cratch
    -0.05
    ãģĭãĤīãģ¯
    -0.05
    jez
    -0.05
    uj
    -0.05
     Giang
    -0.05
    POSITIVE LOGITS
    eyJ
    0.08
    eland
    0.07
    IRR
    0.07
    .GetAsync
    0.06
    ivot
    0.06
    ãĤĵãģ¨
    0.06
    udson
    0.06
    ENU
    0.06
    simulate
    0.06
    urs
    0.06
    Activations Density 0.011%

    No Known Activations