© 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. 17301
    Prev
    Next
    INDEX
    Explanations

    occurrences of commas and periods in 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
    uffers
    -0.07
    ledik
    -0.07
    ENO
    -0.06
     america
    -0.06
     amer
    -0.06
    oux
    -0.06
    .ibatis
    -0.06
    itionally
    -0.06
    uno
    -0.06
    apon
    -0.06
    POSITIVE LOGITS
    utterstock
    0.06
    oming
    0.06
     Gun
    0.06
    cing
    0.06
    Std
    0.06
    ø
    0.06
    685
    0.06
    ulant
    0.06
    declare
    0.06
     Decl
    0.05
    Activations Density 0.026%

    No Known Activations