© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106953
    Prev
    Next
    INDEX
    Explanations

    phrases related to abundance and quantity

    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
    gram
    -0.07
     Cooke
    -0.06
    ivid
    -0.06
    ÑĤÑİ
    -0.06
    管
    -0.06
    âĢł
    -0.06
     ãĤ±
    -0.06
    InterfaceOrientation
    -0.05
    adele
    -0.05
    rib
    -0.05
    POSITIVE LOGITS
    /fw
    0.07
    entes
    0.07
    аÑģ
    0.07
    arters
    0.06
    uml
    0.06
    ķ
    0.06
    èĺ
    0.06
    ìļĶ
    0.06
    ftar
    0.06
     Lor
    0.06
    Activations Density 0.003%

    No Known Activations