© 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. 54575
    Prev
    Next
    INDEX
    Explanations

    references to social organizations and their activities

    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
    erah
    -0.08
     remar
    -0.07
    iyim
    -0.07
    rna
    -0.07
    aney
    -0.07
    abbo
    -0.06
    utters
    -0.06
    asInstanceOf
    -0.06
    ARRIER
    -0.06
    loub
    -0.06
    POSITIVE LOGITS
     haz
    0.07
     Safety
    0.07
     rituals
    0.07
     Alps
    0.07
     traditions
    0.07
     Ritual
    0.07
     frat
    0.07
     tradition
    0.07
     safety
    0.07
     safer
    0.06
    Activations Density 0.002%

    No Known Activations