© 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. 85450
    Prev
    Next
    INDEX
    Explanations

    instances of disappointment or negative experiences

    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
    ãĤ
    -0.07
    /Area
    -0.07
    umas
    -0.07
     оÑģвÑĸ
    -0.06
     Malk
    -0.06
    italize
    -0.06
    areas
    -0.06
    phans
    -0.06
    Ñĥма
    -0.06
    nds
    -0.06
    POSITIVE LOGITS
     news
    0.08
     decision
    0.08
    news
    0.08
     developments
    0.08
     situation
    0.07
     action
    0.07
     announcement
    0.07
     unexpected
    0.06
     happening
    0.06
     outcome
    0.06
    Activations Density 0.023%

    No Known Activations