© 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. 29049
    Prev
    Next
    INDEX
    Explanations

    references to familiar knowledge or shared experiences

    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
    okin
    -0.08
    doch
    -0.07
     Rossi
    -0.07
    ÃŃ
    -0.06
    emi
    -0.06
     Reeves
    -0.06
    óng
    -0.06
    alion
    -0.06
    ÑĢеб
    -0.06
     Revenge
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.09
     today
    0.08
     familiar
    0.08
    today
    0.07
    OrCreate
    0.07
    443
    0.07
     conv
    0.06
    eo
    0.06
     modern
    0.06
     form
    0.06
    Activations Density 0.010%

    No Known Activations