© 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 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. 17-LLAMASCOPE-RES-131K
    11. 89214
    Prev
    Next
    INDEX
    Explanations

    nested curly braces in code

    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
    zag
    -0.09
    âĢ¢↵↵
    -0.08
    istra
    -0.08
    upe
    -0.08
    ÑĤаж
    -0.07
     bạc
    -0.07
    еÑĢÑĪ
    -0.07
    ongan
    -0.07
    еÑĢÑĤи
    -0.07
    xiety
    -0.07
    POSITIVE LOGITS
    :↵
    0.07
    /***/
    0.06
    s
    0.06
    à¯ģ
    0.06
     goto
    0.05
     return
    0.05
    ellig
    0.05
    Âł
    0.05
    ugi
    0.05
    Dirty
    0.05
    Activations Density 0.021%

    No Known Activations