© 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. 73522
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jefferson."

    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
    bage
    -0.06
    gne
    -0.06
    gers
    -0.06
    fur
    -0.06
    매
    -0.06
     mức
    -0.06
    isset
    -0.06
    é»ĺ
    -0.06
    meno
    -0.06
    aret
    -0.06
    POSITIVE LOGITS
    ian
    0.10
    rey
    0.08
    ries
    0.08
    ians
    0.08
    ally
    0.08
    boro
    0.08
    ords
    0.08
    ious
    0.08
    uzzi
    0.08
    zew
    0.07
    Activations Density 0.006%

    No Known Activations