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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 118736
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals named Antonio

    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
    wig
    -0.10
     sobie
    -0.08
    .getOwnProperty
    -0.08
    illard
    -0.08
    κι
    -0.08
    rias
    -0.07
    ëĿ½
    -0.07
    nitÅĻ
    -0.07
    idence
    -0.07
    .decorate
    -0.07
    POSITIVE LOGITS
    ler
    0.06
    angelo
    0.06
     Joshua
    0.06
    utors
    0.06
    lers
    0.06
    ello
    0.06
    ften
    0.06
    inous
    0.05
    ucc
    0.05
    utory
    0.05
    Activations Density 0.003%

    No Known Activations