© 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. 17-LLAMASCOPE-RES-131K
    11. 57581
    Prev
    Next
    INDEX
    Explanations

    HTML link attributes

    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
    avir
    -0.08
    inja
    -0.07
    asma
    -0.07
    ihad
    -0.07
    avo
    -0.06
    273
    -0.06
     volta
    -0.06
    antom
    -0.06
    igos
    -0.06
    kses
    -0.06
    POSITIVE LOGITS
     Marks
    0.06
    .characters
    0.06
    _sdk
    0.06
    egis
    0.06
     Gund
    0.06
    Introduction
    0.06
    æīĢå±ŀ
    0.06
     introduction
    0.05
    ìĨĮê°ľ
    0.05
    帯
    0.05
    Activations Density 0.000%

    No Known Activations