© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119747
    Prev
    Next
    INDEX
    Explanations

    elements related to Facebook API permissions and user data handling

    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
    orex
    -0.07
    hap
    -0.07
    thouse
    -0.06
     Bauer
    -0.06
     Bast
    -0.06
    orda
    -0.06
     citas
    -0.06
    lun
    -0.06
    atar
    -0.06
     Lind
    -0.06
    POSITIVE LOGITS
    facebook
    0.09
     Facebook
    0.09
    Facebook
    0.09
     facebook
    0.08
    .facebook
    0.08
    _facebook
    0.08
    .fb
    0.08
     fb
    0.07
    .oauth
    0.07
     social
    0.07
    Activations Density 0.022%

    No Known Activations