© 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. 56581
    Prev
    Next
    INDEX
    Explanations

    references to academic research or studies

    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
    coon
    -0.07
     Candle
    -0.06
    otto
    -0.06
     Persian
    -0.06
    islav
    -0.06
    ocht
    -0.06
    stoff
    -0.06
    लà¤Ĺ
    -0.06
     Muscle
    -0.06
     extr
    -0.06
    POSITIVE LOGITS
     HIV
    0.07
     UNESCO
    0.07
     micron
    0.07
    UN
    0.07
     UN
    0.06
    .protobuf
    0.06
     Ses
    0.06
    Enumer
    0.06
     villages
    0.06
     univers
    0.06
    Activations Density 0.000%

    No Known Activations