© 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. 15-LLAMASCOPE-RES-131K
    11. 104335
    Prev
    Next
    INDEX
    Explanations

    mentions of various churches

    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
     bevor
    -0.07
    svp
    -0.07
    sert
    -0.07
    okus
    -0.06
     æľ¨
    -0.06
    ήλ
    -0.06
    سات
    -0.06
    oval
    -0.06
    ocommerce
    -0.06
    hub
    -0.06
    POSITIVE LOGITS
    logan
    0.07
     Tire
    0.07
    oid
    0.07
     Blind
    0.07
    anson
    0.06
    paralleled
    0.06
    415
    0.06
     Academ
    0.06
    GS
    0.06
    885
    0.06
    Activations Density 0.009%

    No Known Activations