© 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. 97416
    Prev
    Next
    INDEX
    Explanations

    inquiries about relationships and personal details of celebrities

    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
    ovich
    -0.08
     baiser
    -0.07
     гÑĢо
    -0.07
    icl
    -0.07
    ullet
    -0.07
    erd
    -0.06
    OOM
    -0.06
    ubber
    -0.06
    ESSAGES
    -0.06
     Doub
    -0.06
    POSITIVE LOGITS
     profile
    0.06
     profiles
    0.06
    ledo
    0.06
    ched
    0.05
     rewind
    0.05
     киÑĢ
    0.05
     Chevy
    0.05
     swings
    0.05
     rig
    0.05
     pup
    0.05
    Activations Density 0.009%

    No Known Activations