© 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. 72568
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names associated with individuals, places, and organizations

    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
    ele
    -0.07
    illow
    -0.06
    æµ´
    -0.06
    yg
    -0.06
    uhe
    -0.06
    each
    -0.06
     pur
    -0.06
     harb
    -0.06
    rom
    -0.06
    roma
    -0.06
    POSITIVE LOGITS
    usercontent
    0.08
    DESCRIPTION
    0.07
    ftware
    0.07
    izace
    0.07
    ainen
    0.07
    LEAN
    0.07
    ized
    0.07
     plein
    0.06
    eko
    0.06
    tracking
    0.06
    Activations Density 0.082%

    No Known Activations