© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71445
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iferay
    -0.07
    abar
    -0.07
    upertino
    -0.06
    beth
    -0.06
    DDS
    -0.06
    ало
    -0.06
    STALL
    -0.06
    ollo
    -0.06
     ÑĢайон
    -0.06
    ulum
    -0.06
    POSITIVE LOGITS
    riel
    0.07
    adel
    0.06
    apon
    0.06
    tings
    0.06
    ialog
    0.06
    ħ§
    0.06
    agne
    0.06
    WSC
    0.06
    GT
    0.06
    ér
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.