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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56338
    Prev
    Next
    INDEX
    Explanations

    terms related to social media and professional networking

    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
    cul
    -0.07
    uchs
    -0.07
     cljs
    -0.07
    -Requested
    -0.07
    ault
    -0.07
    omu
    -0.07
    cision
    -0.07
    adele
    -0.06
    iske
    -0.06
    yne
    -0.06
    POSITIVE LOGITS
     Social
    0.08
     social
    0.07
     SOCIAL
    0.07
    Social
    0.07
     Sosyal
    0.07
    ora
    0.06
     Gem
    0.06
    .gf
    0.06
     Gunn
    0.06
    Gem
    0.06
    Activations Density 0.001%

    No Known Activations