© 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. 9-LLAMASCOPE-RES-131K
    11. 95232
    Prev
    Next
    INDEX
    Explanations

    consistently used punctuation, specifically periods

    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
    Ñĥва
    -0.06
    ext
    -0.06
     pending
    -0.06
    @(
    -0.06
     Virgin
    -0.05
    owards
    -0.05
    ÙĪا
    -0.05
    oken
    -0.05
     McConnell
    -0.05
    mul
    -0.05
    POSITIVE LOGITS
    usch
    0.07
    ogn
    0.07
    è³ŀ
    0.07
    ategories
    0.07
    оÑĢÑĤÑĥ
    0.07
    ffe
    0.06
    SURE
    0.06
    opo
    0.06
    ewood
    0.06
    benchmark
    0.06
    Activations Density 0.000%

    No Known Activations