© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70510
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in text, particularly in coding or technical documentation

    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
     Hansen
    -0.07
    å®ı
    -0.07
    oji
    -0.07
    .tk
    -0.06
    )const
    -0.06
    ÃIJ
    -0.06
     tiny
    -0.06
     réfé
    -0.06
     longitud
    -0.06
     Ñĥли
    -0.06
    POSITIVE LOGITS
    0.07
    ụn
    0.06
    AxisAlignment
    0.06
    odom
    0.06
    affer
    0.06
    Ñĸнки
    0.06
    bsolute
    0.06
    _UNS
    0.06
    ellig
    0.06
     bacheca
    0.06
    Activations Density 0.136%

    No Known Activations