© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29086
    Prev
    Next
    INDEX
    Explanations

    terms related to identity and representation in various contexts

    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
    :
    -0.07
     stuff
    -0.07
     various
    -0.07
    à¹īà¸Ĭ
    -0.06
    unding
    -0.06
    äºĽ
    -0.06
     Various
    -0.06
    .dart
    -0.06
    ami
    -0.06
     kinds
    -0.06
    POSITIVE LOGITS
     instance
    0.09
     تصÙħ
    0.08
     nÃło
    0.08
     Instance
    0.08
    EFA
    0.08
     option
    0.07
    instance
    0.07
     item
    0.07
     attempt
    0.07
     кого
    0.07
    Activations Density 0.029%

    No Known Activations