© 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. 127771
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement, spatial relationships, and measurements

    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
    abilia
    -0.07
    reh
    -0.07
    vent
    -0.06
    ÅĻet
    -0.06
    IQ
    -0.06
    ÄĽle
    -0.06
    AMP
    -0.06
    io
    -0.06
    iq
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    POSITIVE LOGITS
     this
    0.07
    this
    0.07
     nÃły
    0.07
    âce
    0.07
    κη
    0.06
    å¹¹ç·ļ
    0.06
    ContentLoaded
    0.06
    illis
    0.06
    typeid
    0.06
    .foo
    0.06
    Activations Density 0.061%

    No Known Activations