© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77906
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    cdnjs
    -0.06
    stem
    -0.06
    wall
    -0.06
    578
    -0.06
     trunk
    -0.06
    arend
    -0.06
    strconv
    -0.06
     if
    -0.06
     commission
    -0.06
    åİ»äºĨ
    -0.05
    POSITIVE LOGITS
    ¥
    0.07
     chaud
    0.07
    άλι
    0.07
    ½Ķ
    0.07
    gens
    0.07
    ordin
    0.07
    oÄŁ
    0.07
    üny
    0.06
    å¯
    0.06
    !!!!↵↵
    0.06
    Activations Density 0.001%

    No Known Activations