© 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. 9-LLAMASCOPE-RES-131K
    11. 97719
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and feelings related to past locations and significant life events

    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
     dikke
    -0.08
    омÑĸ
    -0.07
    ären
    -0.07
    formance
    -0.07
     liebe
    -0.07
    uze
    -0.07
     ìĸ
    -0.07
    äre
    -0.07
    osas
    -0.07
    egov
    -0.07
    POSITIVE LOGITS
    æķ
    0.05
     gam
    0.05
    rar
    0.05
    Unmount
    0.05
     Atlas
    0.05
     too
    0.05
    ;element
    0.05
     heroine
    0.05
    itzer
    0.05
     courtesy
    0.05
    Activations Density 0.034%

    No Known Activations