© 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. 126645
    Prev
    Next
    INDEX
    Explanations

    phrases related to baseball lineups and player positions

    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
    istrovstvÃŃ
    -0.07
     hiring
    -0.06
     hire
    -0.06
    genden
    -0.06
    kee
    -0.06
     Klaus
    -0.06
    HostException
    -0.06
    -calendar
    -0.06
     اÙĦعÙħ
    -0.06
    ength
    -0.06
    POSITIVE LOGITS
     ASSIGN
    0.07
    isi
    0.06
    _MISC
    0.06
    719
    0.06
     crack
    0.06
     Formation
    0.06
     jes
    0.06
    تش
    0.06
    _assoc
    0.06
    .getLine
    0.06
    Activations Density 0.003%

    No Known Activations