Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95933
    Prev
    Next
    INDEX
    Explanations

    HTML table cells

    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
    avig
    -0.06
    å»Ĭ
    -0.06
    lover
    -0.06
    handle
    -0.06
    ätz
    -0.06
    perf
    -0.06
    cl
    -0.06
    éł
    -0.06
     lidi
    -0.06
    оже
    -0.06
    POSITIVE LOGITS
    .gwt
    0.07
    czas
    0.06
    apos
    0.06
     Alberto
    0.06
    ãģ¡ãģ¯
    0.06
     deco
    0.06
    .LookAndFeel
    0.06
    측
    0.06
    igner
    0.06
    pler
    0.06
    Activations Density 0.005%

    No Known Activations