© 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 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. 119247
    Prev
    Next
    INDEX
    Explanations

    positive sentiments associated with sports events

    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
    å¤ĩ
    -0.07
    _HINT
    -0.06
     sco
    -0.06
    rado
    -0.06
    admin
    -0.05
     Zar
    -0.05
     poh
    -0.05
    acad
    -0.05
     compat
    -0.05
     mono
    -0.05
    POSITIVE LOGITS
    edi
    0.08
    batim
    0.07
    arium
    0.07
    lest
    0.07
    hazi
    0.07
    xab
    0.07
     geil
    0.07
    Æ°á»Ľng
    0.07
    pcl
    0.07
     watching
    0.07
    Activations Density 0.001%

    No Known Activations