© 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. 88149
    Prev
    Next
    INDEX
    Explanations

    mentions of Facebook and its relevance in various contexts

    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
     versa
    -0.06
    zar
    -0.05
    bx
    -0.05
    unities
    -0.05
    abox
    -0.05
    .toolbox
    -0.05
    µ¬
    -0.05
    avic
    -0.05
    yun
    -0.05
     ax
    -0.05
    POSITIVE LOGITS
    lander
    0.07
    -preview
    0.07
    .XR
    0.07
    .Bunifu
    0.07
    ÙĴس
    0.07
     autogenerated
    0.06
     edin
    0.06
     destinationViewController
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    959
    0.06
    Activations Density 0.000%

    No Known Activations