© 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. 84223
    Prev
    Next
    INDEX
    Explanations

    references to gaming experiences and multiplayer interactions

    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
    ANTE
    -0.07
    lien
    -0.07
    à¹ģà¸ľ
    -0.07
    AWN
    -0.07
    INCREMENT
    -0.07
    κÎŃ
    -0.07
    pread
    -0.06
     Fon
    -0.06
    REATED
    -0.06
    QUARE
    -0.06
    POSITIVE LOGITS
    entiful
    0.07
     formations
    0.07
     screenshot
    0.06
     playing
    0.06
     play
    0.06
     veteran
    0.06
     Formation
    0.06
    seg
    0.06
    -playing
    0.06
     tanks
    0.06
    Activations Density 0.007%

    No Known Activations