© 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. 104142
    Prev
    Next
    INDEX
    Explanations

    punctuation and syntactical structures 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
    åı«
    -0.10
     called
    -0.09
    called
    -0.09
    loquent
    -0.09
     Called
    -0.08
     termed
    -0.08
    Called
    -0.08
     llam
    -0.07
    ynet
    -0.07
    -called
    -0.07
    POSITIVE LOGITS
    ÂĿ
    0.07
    .si
    0.07
    âĦ¢
    0.06
     PointF
    0.06
    assin
    0.06
    (TM
    0.06
    bole
    0.06
    жив
    0.06
    stead
    0.06
    bourne
    0.06
    Activations Density 0.032%

    No Known Activations