© 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. 22-LLAMASCOPE-RES-131K
    11. 3794
    Prev
    Next
    INDEX
    Explanations

    references to specific events or locations, particularly those related to historical or cultural significance

    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
    384
    -0.06
    abelle
    -0.06
    267
    -0.06
    åĴ²
    -0.06
    iolet
    -0.06
    itations
    -0.06
    iw
    -0.06
     Wolverine
    -0.06
    tery
    -0.06
    ública
    -0.06
    POSITIVE LOGITS
    dam
    0.11
    дам
    0.07
    graduate
    0.07
    adem
    0.07
    damn
    0.06
     minus
    0.06
    eldorf
    0.06
    greSQL
    0.06
    Ø®Ùħ
    0.06
     gre
    0.06
    Activations Density 0.002%

    No Known Activations