© 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. 93785
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or teams in sports contexts

    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
    baru
    -0.07
    erdem
    -0.07
    ifestyles
    -0.06
    ore
    -0.06
    ANJI
    -0.06
     ÙħÙĤاÙħ
    -0.06
    hots
    -0.05
    apixel
    -0.05
    .Std
    -0.05
    acter
    -0.05
    POSITIVE LOGITS
     team
    0.11
     Team
    0.10
    team
    0.10
    Team
    0.09
    ãĥģãĥ¼ãĥł
    0.08
     Group
    0.08
    _team
    0.08
    -team
    0.08
    ãĥ¼ãĥģ
    0.08
    íĮĢ
    0.07
    Activations Density 0.018%

    No Known Activations