© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98356
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports teams and their players

    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
    cope
    -0.06
     unb
    -0.06
    ropa
    -0.06
    antz
    -0.06
     Bloc
    -0.05
    aturity
    -0.05
     Pan
    -0.05
    horn
    -0.05
    ByUsername
    -0.05
    ocrates
    -0.05
    POSITIVE LOGITS
    age
    0.07
    vip
    0.07
    رÙĪز
    0.07
    rieb
    0.07
    avl
    0.07
     Minh
    0.06
    -Cs
    0.06
    ãĥ³ãĥģ
    0.06
    åŃ
    0.06
    248
    0.06
    Activations Density 0.008%

    No Known Activations