© 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. 60635
    Prev
    Next
    INDEX
    Explanations

    references to payment methods and credit card acceptance

    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
     Replacement
    -0.06
    acter
    -0.06
     Mall
    -0.06
    tright
    -0.06
    ights
    -0.06
    uer
    -0.06
    antal
    -0.06
    etros
    -0.06
     Sal
    -0.05
    bie
    -0.05
    POSITIVE LOGITS
    /*č↵
    0.08
    оÑĢон
    0.08
     accepted
    0.07
    #
    0.07
    .defer
    0.07
    accepted
    0.07
    <fieldset
    0.07
    slideDown
    0.07
     ÙĤب
    0.07
    emachine
    0.07
    Activations Density 0.013%

    No Known Activations