© 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 EvalsExportsinterp-engineNEWAPI 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. 123720
    Prev
    Next
    INDEX
    Explanations

    names of professional organizations and associations

    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
    ìĦłìĿĦ
    -0.08
     Pazar
    -0.08
    иÑĤелÑĮной
    -0.08
    anded
    -0.07
    ddb
    -0.07
    acf
    -0.07
    ceb
    -0.07
    arging
    -0.07
    erp
    -0.07
    (&$
    -0.07
    POSITIVE LOGITS
     twice
    0.07
     membership
    0.06
     where
    0.06
    eland
    0.06
     whose
    0.06
    )&&
    0.06
     active
    0.06
     Inner
    0.06
    -Out
    0.05
     Crush
    0.05
    Activations Density 0.020%

    No Known Activations