© 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. 59167
    Prev
    Next
    INDEX
    Explanations

    sequences of characters and punctuation, particularly code-like syntax

    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
    ieder
    -0.07
    rien
    -0.07
    BS
    -0.06
    оÑĩ
    -0.06
     crown
    -0.06
    oft
    -0.06
    bs
    -0.06
     leak
    -0.06
    ffi
    -0.06
     BS
    -0.06
    POSITIVE LOGITS
     fflush
    0.07
    taj
    0.07
    	fflush
    0.07
    inity
    0.06
    azi
    0.06
    vais
    0.06
    iž
    0.06
     Bund
    0.06
     bund
    0.06
    taire
    0.06
    Activations Density 0.039%

    No Known Activations