© 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. 4943
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or liking

    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
    ç¼
    -0.07
    оÑĥ
    -0.07
     lẽ
    -0.07
    stroy
    -0.07
    lette
    -0.07
    ivering
    -0.07
    rej
    -0.07
    culo
    -0.07
    æij
    -0.07
    é¬
    -0.07
    POSITIVE LOGITS
     personally
    0.07
     using
    0.07
     use
    0.06
     mine
    0.06
     ours
    0.06
     to
    0.06
     this
    0.06
     because
    0.06
    ao
    0.06
     fol
    0.06
    Activations Density 0.013%

    No Known Activations