© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89401
    Prev
    Next
    INDEX
    Explanations

    themes related to altruism and reciprocity in 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
     model
    -0.06
     glo
    -0.06
    /browser
    -0.06
    asso
    -0.06
     Mae
    -0.06
    born
    -0.05
    aea
    -0.05
    alle
    -0.05
    ae
    -0.05
     Model
    -0.05
    POSITIVE LOGITS
    yš
    0.07
    åѦä¼ļ
    0.07
    [from
    0.07
    天åłĤ
    0.07
    Locked
    0.07
    ewis
    0.06
    exchange
    0.06
    Ùĥس
    0.06
     entitlement
    0.06
     erotico
    0.06
    Activations Density 0.049%

    No Known Activations