© 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. 128040
    Prev
    Next
    INDEX
    Explanations

    content related to product details and terms of service

    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
    ãĥ¼ãĥŀ
    -0.07
    cxx
    -0.07
    ;amp
    -0.06
    vfs
    -0.06
    tmpl
    -0.06
    Pts
    -0.06
     Ballet
    -0.06
    ÑħÑĥ
    -0.06
    umbles
    -0.06
    âĦĸ
    -0.05
    POSITIVE LOGITS
     McCart
    0.07
    pekt
    0.07
     product
    0.07
     Shot
    0.07
     gums
    0.07
     descriptions
    0.07
    ynn
    0.06
    setDescription
    0.06
    ála
    0.06
     gum
    0.06
    Activations Density 0.008%

    No Known Activations