© 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. 15-LLAMASCOPE-RES-131K
    11. 89902
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly those that indicate dialogue or emotional expression

    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
    elu
    -0.07
     teb
    -0.07
    νή
    -0.07
    ebo
    -0.07
    ãģ£ãģį
    -0.07
    ocaly
    -0.07
    bins
    -0.07
    leans
    -0.07
    ael
    -0.07
    INGLE
    -0.07
    POSITIVE LOGITS
     spoken
    0.06
     Sav
    0.05
     sounds
    0.05
     Dixon
    0.05
     Kaz
    0.05
    142
    0.05
     sav
    0.05
    annah
    0.05
     holding
    0.05
     bus
    0.05
    Activations Density 0.025%

    No Known Activations