© 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. 2560
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional connections and personal 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
    uze
    -0.09
    asu
    -0.08
    dden
    -0.08
    cak
    -0.08
    elik
    -0.08
     Ekon
    -0.08
    PathComponent
    -0.08
    UILTIN
    -0.08
    ?action
    -0.07
    eking
    -0.07
    POSITIVE LOGITS
     interest
    0.08
    lesc
    0.07
    uzz
    0.06
     concern
    0.06
     fond
    0.06
     concerns
    0.06
     uneasy
    0.06
     toler
    0.06
     dual
    0.06
     kin
    0.06
    Activations Density 0.035%

    No Known Activations