© 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. 58003
    Prev
    Next
    INDEX
    Explanations

    references to countries and national teams in a sports context

    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
    urs
    -0.07
    hoot
    -0.06
    _formats
    -0.06
    inning
    -0.06
    ược
    -0.06
    çĩŁ
    -0.06
    imus
    -0.06
     xu
    -0.06
     governing
    -0.06
    fos
    -0.06
    POSITIVE LOGITS
     representation
    0.11
     Representation
    0.10
     send
    0.08
    Representation
    0.08
     delegation
    0.08
     represented
    0.08
     Sending
    0.08
    representation
    0.08
     entries
    0.08
    represented
    0.07
    Activations Density 0.032%

    No Known Activations