© 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. 5-LLAMASCOPE-RES-131K
    11. 125771
    Prev
    Next
    INDEX
    Explanations

    references to the TV show "Peaky Blinders" and its related content

    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
    esan
    -0.07
    ÑıÑĩ
    -0.07
    afia
    -0.07
    imately
    -0.07
    listing
    -0.07
    engkap
    -0.07
    inati
    -0.07
    visualization
    -0.07
    storybook
    -0.07
    ataire
    -0.07
    POSITIVE LOGITS
    anks
    0.06
     Merchant
    0.06
    akis
    0.06
    083
    0.05
    fern
    0.05
    ay
    0.05
     autop
    0.05
    ven
    0.05
    mand
    0.05
    460
    0.05
    Activations Density 0.000%

    No Known Activations