© 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. 27698
    Prev
    Next
    INDEX
    Explanations

    locations or place names within a text

    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
    éijij
    -0.07
    ocale
    -0.07
    аÑĢан
    -0.07
    avs
    -0.07
    ihan
    -0.07
    izona
    -0.07
     ìĶ¨
    -0.07
    ossa
    -0.07
    ewise
    -0.06
    abant
    -0.06
    POSITIVE LOGITS
    196
    0.06
     born
    0.06
     Born
    0.06
    197
    0.06
     rural
    0.06
    /st
    0.06
    192
    0.06
    198
    0.05
    194
    0.05
     curiosity
    0.05
    Activations Density 0.007%

    No Known Activations