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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95543
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and collaborative efforts

    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
    ebra
    -0.07
    atem
    -0.06
    ãĥĸãĥª
    -0.06
     Funeral
    -0.06
    Ùİت
    -0.06
     indir
    -0.06
    asser
    -0.06
    ière
    -0.06
     Stripe
    -0.06
    loy
    -0.06
    POSITIVE LOGITS
    /gtest
    0.07
    346
    0.07
    celik
    0.07
    %č↵
    0.07
    620
    0.07
    569
    0.06
    kuk
    0.06
    326
    0.06
    rium
    0.06
    yz
    0.06
    Activations Density 0.008%

    No Known Activations