© 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. 29448
    Prev
    Next
    INDEX
    Explanations

    instances of foreign entities or references related to individuals or organizations

    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
    æĺŃ
    -0.07
    469
    -0.07
     Winning
    -0.07
    rogram
    -0.07
    aan
    -0.06
     Cage
    -0.06
    inox
    -0.06
    htub
    -0.06
    .Len
    -0.06
    oppins
    -0.06
    POSITIVE LOGITS
    avery
    0.07
    _FOREACH
    0.06
    etti
    0.06
    ousse
    0.06
    uent
    0.06
    Pen
    0.06
    Batch
    0.06
     pen
    0.06
    deb
    0.06
     Pen
    0.06
    Activations Density 0.002%

    No Known Activations