© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41183
    Prev
    Next
    INDEX
    Explanations

    information regarding travel-related concerns and facilities in Tibet

    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
    strup
    -0.08
    amina
    -0.07
    udd
    -0.06
     pipe
    -0.06
    åı¤
    -0.06
    Pipe
    -0.06
    elle
    -0.06
    assage
    -0.06
     tally
    -0.06
     Hispanic
    -0.06
    POSITIVE LOGITS
     currency
    0.09
     nationals
    0.08
    LANGUAGE
    0.08
     visitor
    0.07
     Currency
    0.07
     customs
    0.07
     Lan
    0.07
     safety
    0.07
    afety
    0.07
    chio
    0.07
    Activations Density 0.051%

    No Known Activations