© 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. 118840
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their associated cultural products

    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
    anson
    -0.07
    emailer
    -0.07
     Си
    -0.07
    adge
    -0.07
    ioni
    -0.06
    ORITY
    -0.06
     callable
    -0.06
    teri
    -0.06
     Glob
    -0.06
    lero
    -0.06
    POSITIVE LOGITS
     version
    0.07
    -only
    0.07
    -market
    0.07
    -version
    0.07
     equivalent
    0.07
    version
    0.07
     market
    0.07
     Equivalent
    0.07
    /world
    0.07
    çīĪ
    0.07
    Activations Density 0.016%

    No Known Activations