© 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. 81595
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Ulrich" and its variants

    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
    ocio
    -0.08
     Kral
    -0.07
    affen
    -0.07
    kö
    -0.07
    ÑĤÑĮ
    -0.07
    older
    -0.07
    intree
    -0.07
    voj
    -0.06
    nim
    -0.06
    rous
    -0.06
    POSITIVE LOGITS
    terior
    0.08
    imately
    0.08
    tras
    0.08
    trasound
    0.08
    rich
    0.07
    imate
    0.07
    bert
    0.07
     Kul
    0.07
    fa
    0.06
    anza
    0.06
    Activations Density 0.010%

    No Known Activations