© 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. 17-LLAMASCOPE-RES-131K
    11. 62001
    Prev
    Next
    INDEX
    Explanations

    mentions of gaming and related activities

    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
    ings
    -0.07
    vt
    -0.07
    utz
    -0.06
    kü
    -0.06
    jem
    -0.06
    aire
    -0.06
    aires
    -0.06
    á»ĩnh
    -0.06
    icer
    -0.06
    poke
    -0.06
    POSITIVE LOGITS
    -console
    0.07
    iye
    0.07
    rrha
    0.07
    752
    0.06
    tainment
    0.06
    740
    0.06
    asher
    0.06
    à¸ģระ
    0.06
    ota
    0.06
    ضÛĮ
    0.06
    Activations Density 0.004%

    No Known Activations