© 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. 107213
    Prev
    Next
    INDEX
    Explanations

    phrases concerning sports events and match outcomes

    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
     Hod
    -0.06
    ampoo
    -0.06
    pure
    -0.06
    imestone
    -0.06
    ingham
    -0.06
    лин
    -0.06
     Harper
    -0.06
    auc
    -0.06
    Pure
    -0.06
    .createSequentialGroup
    -0.06
    POSITIVE LOGITS
    Ħ
    0.07
    lak
    0.07
    iten
    0.07
    uja
    0.07
    ÑĢел
    0.06
    iki
    0.06
    THR
    0.06
    æĪ²
    0.06
    ác
    0.06
    æݪ
    0.06
    Activations Density 0.014%

    No Known Activations