© 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. 77272
    Prev
    Next
    INDEX
    Explanations

    phrases that convey personal experiences and relationships

    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
    andel
    -0.07
    weit
    -0.07
    uali
    -0.07
    ollipop
    -0.07
    aleur
    -0.06
     води
    -0.06
    orrow
    -0.06
    chez
    -0.06
    inja
    -0.06
    åĤ
    -0.06
    POSITIVE LOGITS
     avid
    0.09
     fond
    0.08
     lifelong
    0.07
     loves
    0.07
     lover
    0.07
     love
    0.07
     interest
    0.07
     fans
    0.07
     lovers
    0.07
     interests
    0.06
    Activations Density 0.039%

    No Known Activations