© 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. 120508
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically place names

    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
    nty
    -0.06
    PV
    -0.06
    elf
    -0.06
    ucken
    -0.06
     Poz
    -0.06
    heed
    -0.06
    utsch
    -0.05
    맥
    -0.05
     ↵
    -0.05
    ields
    -0.05
    POSITIVE LOGITS
    -based
    0.09
    shire
    0.09
    ιÏĩ
    0.08
     location
    0.07
    -area
    0.07
     facility
    0.07
    bert
    0.07
    facility
    0.07
    Unmount
    0.07
    -bound
    0.06
    Activations Density 0.022%

    No Known Activations