© 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. 5530
    Prev
    Next
    INDEX
    Explanations

    events involving personal interactions and emotional moments

    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
    paque
    -0.09
    fte
    -0.07
    vro
    -0.07
    odon
    -0.07
    ghan
    -0.07
    zac
    -0.07
    chner
    -0.07
    rah
    -0.07
    olid
    -0.07
    ceptar
    -0.07
    POSITIVE LOGITS
     visit
    0.10
     arrival
    0.09
     arrive
    0.09
     visits
    0.09
     arrivals
    0.08
     visita
    0.08
     door
    0.08
     arrived
    0.08
     demanding
    0.08
     arriv
    0.08
    Activations Density 0.046%

    No Known Activations