© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    references to people, particularly their birth information and associated details

    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
     hala
    -0.08
    ãĥŃãĥ³
    -0.07
    azzi
    -0.07
    جاÙħ
    -0.07
    opak
    -0.07
    iç
    -0.07
    agma
    -0.07
    ottie
    -0.06
    caa
    -0.06
    ÙĤب
    -0.06
    POSITIVE LOGITS
    198
    0.09
    197
    0.09
    201
    0.08
    199
    0.08
    202
    0.07
    196
    0.07
    bracht
    0.06
    0.06
    156
    0.06
    200
    0.06
    Activations Density 0.000%

    No Known Activations