© 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. 9-LLAMASCOPE-RES-131K
    11. 95809
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain formatting elements, indicating a focus on structure or quotation in text

    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
    .Tables
    -0.07
    icked
    -0.07
     Oper
    -0.06
    quared
    -0.06
    ToWorld
    -0.06
    ushing
    -0.06
    501
    -0.06
    ye
    -0.06
     DJ
    -0.06
    ols
    -0.06
    POSITIVE LOGITS
    Ī
    0.07
     ÙĨس
    0.07
     Jaune
    0.07
     getopt
    0.07
    PropertyDescriptor
    0.07
    dag
    0.07
    uster
    0.07
    abwe
    0.07
    afb
    0.06
    tek
    0.06
    Activations Density 0.000%

    No Known Activations