© 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. 76561
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Sur" and its variations, indicating a focus on surveillance or monitoring 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
    aukee
    -0.08
    igkeit
    -0.08
    bare
    -0.07
    uras
    -0.07
    ches
    -0.07
    esium
    -0.07
     Idol
    -0.07
    é§IJ
    -0.07
     Neighborhood
    -0.07
    olist
    -0.07
    POSITIVE LOGITS
    prisingly
    0.09
    çĶ²
    0.07
    -sur
    0.07
     sup
    0.07
    prising
    0.07
    veys
    0.06
     dụng
    0.06
    oner
    0.06
    sets
    0.06
    icate
    0.06
    Activations Density 0.008%

    No Known Activations