© 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. 124679
    Prev
    Next
    INDEX
    Explanations

    expressions of positive emotions about products or services

    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
    essor
    -0.07
    usk
    -0.06
    иÑĤоÑĢ
    -0.06
    ê´Ģ
    -0.06
    EAR
    -0.06
    aim
    -0.06
     odds
    -0.06
    oman
    -0.06
    ppe
    -0.06
    aman
    -0.05
    POSITIVE LOGITS
     overall
    0.07
    eldom
    0.07
    Prompt
    0.07
    Ownership
    0.07
    :System
    0.07
    uards
    0.07
     baja
    0.07
    asha
    0.07
     purchased
    0.06
    Purchase
    0.06
    Activations Density 0.013%

    No Known Activations