© 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. 15-LLAMASCOPE-RES-131K
    6. 487
    Prev
    Next
    INDEX
    Explanations

    timestamps and numeric values in the 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
    аÑĤоÑĢ
    -0.07
    pedia
    -0.06
     caller
    -0.06
    goog
    -0.06
    ottes
    -0.06
     Caller
    -0.06
    appen
    -0.06
    oard
    -0.06
    owie
    -0.06
    omatic
    -0.06
    POSITIVE LOGITS
    æķħ
    0.07
    aha
    0.06
    éĩĩ
    0.06
     onAnimation
    0.06
    izon
    0.06
    رÛĮز
    0.06
     Lois
    0.06
    upa
    0.06
    á»ģn
    0.06
    module
    0.06
    Activations Density 0.003%

    No Known Activations