© 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. 105674
    Prev
    Next
    INDEX
    Explanations

    phrases indicating communication and social interaction

    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
    füg
    -0.07
    éĽĨä¸Ń
    -0.07
    amm
    -0.07
    ilig
    -0.06
    yleft
    -0.06
    erli
    -0.06
     Sage
    -0.06
    endi
    -0.06
    urette
    -0.06
    asil
    -0.06
    POSITIVE LOGITS
     together
    0.11
     Together
    0.10
    Together
    0.09
    ä¸Ģèµ·
    0.09
     spolu
    0.09
    gether
    0.08
     nhau
    0.08
     mutual
    0.08
    äºĴ
    0.08
     mutually
    0.07
    Activations Density 0.059%

    No Known Activations