© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75730
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain programming syntax elements

    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
    âĢ¢↵↵
    -0.09
    ******↵↵
    -0.07
    -↵↵
    -0.07
    rysler
    -0.06
    inka
    -0.06
    ưu
    -0.06
    /tiny
    -0.06
    umas
    -0.06
    FINE
    -0.06
    dff
    -0.06
    POSITIVE LOGITS
     etc
    0.10
     \↵
    0.08
     ↵
    0.07
    á»ı
    0.07
    침
    0.06
    etc
    0.06
     hol
    0.06
    ÑģÑĤи
    0.06
    '↵
    0.06
    .DrawLine
    0.06
    Activations Density 0.022%

    No Known Activations