Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43973
    Prev
    Next
    INDEX
    Explanations

    references to criminal activity and legal proceedings

    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
    à¸Ļม
    -0.06
    jud
    -0.06
    .MixedReality
    -0.05
    ĵįä½ľ
    -0.05
     bureaucr
    -0.05
    isl
    -0.05
     Inspection
    -0.05
     inspections
    -0.05
    ضاء
    -0.05
     scand
    -0.05
    POSITIVE LOGITS
     text
    0.11
     argument
    0.08
     intoxicated
    0.08
     Text
    0.08
     arguments
    0.08
     drinking
    0.08
     TEXT
    0.08
     texts
    0.08
     driving
    0.07
     meth
    0.07
    Activations Density 0.027%

    No Known Activations