© 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. 60145
    Prev
    Next
    INDEX
    Explanations

    references to a specific country and its population characteristics

    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
    uf
    -0.07
    ucc
    -0.06
    ám
    -0.06
     StringBuffer
    -0.06
    /wp
    -0.06
    Spanish
    -0.06
    æ®Ĭ
    -0.06
    TAG
    -0.06
    áu
    -0.06
     overs
    -0.06
    POSITIVE LOGITS
     вида
    0.07
     national
    0.07
    ogne
    0.07
     nackte
    0.06
    kre
    0.06
     ces
    0.06
     arrang
    0.06
     shim
    0.06
    unde
    0.06
    utz
    0.06
    Activations Density 0.001%

    No Known Activations