© 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. 93942
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of people's friendliness and helpfulness

    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
    wang
    -0.07
    ame
    -0.06
    zie
    -0.06
    (&(
    -0.06
    AME
    -0.06
    564
    -0.06
    eggies
    -0.06
    ponsored
    -0.06
    phies
    -0.05
    émon
    -0.05
    POSITIVE LOGITS
     friendly
    0.10
    friendly
    0.09
     Friendly
    0.09
     hospitality
    0.08
    -friendly
    0.08
    Friendly
    0.08
     welcoming
    0.08
     genuine
    0.07
     staff
    0.07
     Helpful
    0.07
    Activations Density 0.056%

    No Known Activations