© 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 EvalsExportsAPI 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. 106681
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and landmarks

    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
    —if
    -0.06
    aidu
    -0.06
     Pradesh
    -0.06
    County
    -0.06
    odge
    -0.06
    æĬŀ
    -0.06
     counties
    -0.06
    CastException
    -0.06
    ActivityResult
    -0.06
     COUNTY
    -0.06
    POSITIVE LOGITS
     street
    0.10
     Street
    0.10
     Market
    0.08
    itan
    0.07
    itten
    0.07
     Parade
    0.07
    izontal
    0.07
    kiye
    0.07
    Street
    0.07
    ople
    0.07
    Activations Density 0.061%

    No Known Activations