© 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. 94834
    Prev
    Next
    INDEX
    Explanations

    references to community health and societal structure issues

    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
     reportedly
    -0.08
     Suff
    -0.07
     allegedly
    -0.06
     aforementioned
    -0.06
    ÅĽci
    -0.06
    loor
    -0.06
     interpre
    -0.06
     Drain
    -0.06
    opal
    -0.06
    lemen
    -0.06
    POSITIVE LOGITS
    ANE
    0.07
     Visible
    0.07
     conventional
    0.06
    undo
    0.06
    oleÄį
    0.06
    iet
    0.06
     because
    0.06
    gw
    0.06
    паÑĤ
    0.06
    isa
    0.06
    Activations Density 0.045%

    No Known Activations