© 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. 79998
    Prev
    Next
    INDEX
    Explanations

    the name "Albert" in various contexts and instances throughout the text

    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
    finder
    -0.07
    upe
    -0.07
    eldon
    -0.07
     Steph
    -0.07
    erland
    -0.07
    gere
    -0.07
    throw
    -0.07
    εÏģÏĮ
    -0.07
    nergy
    -0.07
    forgettable
    -0.07
    POSITIVE LOGITS
    ine
    0.09
    ans
    0.08
    ldr
    0.08
    son
    0.07
    ton
    0.07
    ory
    0.07
    arians
    0.07
    tre
    0.07
    ome
    0.07
    querque
    0.07
    Activations Density 0.004%

    No Known Activations