© 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. 108331
    Prev
    Next
    INDEX
    Explanations

    references to property features and specifications

    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
    anders
    -0.07
    欣
    -0.06
    bes
    -0.06
    agli
    -0.06
    illard
    -0.06
    ãĤĴè¦ĭãĤĭ
    -0.06
    éļĽ
    -0.06
    azard
    -0.06
     khÃŃ
    -0.06
    ç¬
    -0.06
    POSITIVE LOGITS
     Trem
    0.07
    yte
    0.06
    paginate
    0.06
     baths
    0.06
     organic
    0.06
    unma
    0.06
    662
    0.06
    783
    0.05
    979
    0.05
    undy
    0.05
    Activations Density 0.001%

    No Known Activations