© 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. 130987
    Prev
    Next
    INDEX
    Explanations

    references to social networks and their impact on 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
    å¡ļ
    -0.08
    kov
    -0.08
    indent
    -0.07
    #ad
    -0.07
    oub
    -0.07
    ındır
    -0.07
    ddit
    -0.07
    odel
    -0.07
    -UA
    -0.07
    åıĤ
    -0.07
    POSITIVE LOGITS
     friends
    0.14
     Friends
    0.14
     contacts
    0.13
     friendships
    0.13
     networks
    0.11
     friendship
    0.11
    Friends
    0.11
    friends
    0.11
     friend
    0.11
     Contacts
    0.10
    Activations Density 0.147%

    No Known Activations