© 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. 39142
    Prev
    Next
    INDEX
    Explanations

    references to oral history and genealogical research

    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
     Inspection
    -0.06
     Wallpaper
    -0.06
    æĽľ
    -0.06
     absentee
    -0.06
    ulings
    -0.06
     Dummy
    -0.06
    /xhtml
    -0.06
    ýn
    -0.06
    æ¼Ķ
    -0.06
     æľĪ
    -0.06
    POSITIVE LOGITS
     interview
    0.10
     recording
    0.10
     interviewer
    0.09
     Oral
    0.09
     interviews
    0.09
     Interview
    0.09
    Recording
    0.08
     Recording
    0.08
     oral
    0.08
    Interview
    0.08
    Activations Density 0.015%

    No Known Activations