© 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. 73974
    Prev
    Next
    INDEX
    Explanations

    references to historical events and social conditions relating to public health and community structure

    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
    urent
    -0.07
    ardu
    -0.07
    .Emit
    -0.07
    REEN
    -0.07
    ulp
    -0.07
    ãĤ¤ãĥī
    -0.06
     sát
    -0.06
    reopen
    -0.06
    riott
    -0.06
    oppel
    -0.06
    POSITIVE LOGITS
     presence
    0.14
     arrived
    0.13
     arrival
    0.13
     arrive
    0.13
     arrives
    0.12
     arriving
    0.11
     introduction
    0.10
     Presence
    0.10
    presence
    0.10
     lleg
    0.10
    Activations Density 0.110%

    No Known Activations