© 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 EvalsExportsinterp-engineNEWAPI 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. 62396
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Anna"

    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
    aina
    -0.08
    롯
    -0.07
    ena
    -0.07
    INES
    -0.07
     Podesta
    -0.07
     EXEMPLARY
    -0.07
    plash
    -0.07
    upertino
    -0.07
    ariant
    -0.07
    emean
    -0.07
    POSITIVE LOGITS
    173
    0.05
     decor
    0.05
    owitz
    0.05
     Geh
    0.05
    cession
    0.05
    oui
    0.05
    ajs
    0.05
    ÙĦÛĮت
    0.05
    rik
    0.05
    artner
    0.05
    Activations Density 0.042%

    No Known Activations