© 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. 95188
    Prev
    Next
    INDEX
    Explanations

    references to gameplay mechanics and item interactions in video games

    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
     Lage
    -0.08
    erap
    -0.07
    URLException
    -0.07
    877
    -0.07
    chn
    -0.06
    è¨ĢãģĦ
    -0.06
    oog
    -0.06
     GenerationType
    -0.06
    éĮĦ
    -0.06
    .accel
    -0.06
    POSITIVE LOGITS
    arty
    0.06
    ,[],
    0.06
    uther
    0.06
    è¡Į
    0.06
    ement
    0.06
    Hist
    0.06
    Vent
    0.06
     row
    0.06
     xsi
    0.05
    PCM
    0.05
    Activations Density 0.008%

    No Known Activations