© 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. 92887
    Prev
    Next
    INDEX
    Explanations

    references to gambling

    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
     Walton
    -0.08
    sdale
    -0.08
    omanip
    -0.07
    ãĤ§
    -0.07
    ãģĦãĤĭ
    -0.07
    eous
    -0.07
    ymb
    -0.07
    emann
    -0.07
    ointment
    -0.07
    emo
    -0.07
    POSITIVE LOGITS
    tainment
    0.07
    ellen
    0.07
    bones
    0.07
    .LookAndFeel
    0.07
    mtree
    0.06
    zn
    0.06
     Jacqu
    0.06
    -thumbnails
    0.06
    ê
    0.06
    gren
    0.06
    Activations Density 0.002%

    No Known Activations