© 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. 82333
    Prev
    Next
    INDEX
    Explanations

    punctuation and common sentence structures, particularly excessive or unusual comma usage

    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
     iÅŁte
    -0.07
     needless
    -0.06
    uo
    -0.06
     Jou
    -0.06
     Sche
    -0.06
     íı
    -0.06
    u
    -0.06
    _FREQUENCY
    -0.05
    PLUS
    -0.05
    ...
    -0.05
    POSITIVE LOGITS
    contro
    0.09
    .scalablytyped
    0.08
    ambi
    0.07
    alar
    0.07
    ibraltar
    0.07
    ζί
    0.07
    -tm
    0.07
     jur
    0.07
    ToProps
    0.07
    éal
    0.07
    Activations Density 0.020%

    No Known Activations