© 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. 17-LLAMASCOPE-RES-131K
    11. 75619
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "know" indicating a focus on familiarity and understanding of others

    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
    곤
    -0.08
    ï¼Ń
    -0.07
    ardy
    -0.07
    ož
    -0.07
    }elseif
    -0.07
    anzi
    -0.07
    .blob
    -0.07
     Preis
    -0.07
    utom
    -0.07
    /items
    -0.07
    POSITIVE LOGITS
    earer
    0.08
     ins
    0.07
    ledged
    0.06
     Lod
    0.06
     Gle
    0.06
    orig
    0.06
    egra
    0.06
    ieve
    0.06
    ements
    0.06
     nhau
    0.06
    Activations Density 0.006%

    No Known Activations