© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94277
    Prev
    Next
    INDEX
    Explanations

    references to exploitation and enslavement

    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
    aida
    -0.08
    .scalablytyped
    -0.07
    andin
    -0.07
    idor
    -0.07
    reds
    -0.07
    argout
    -0.07
    zych
    -0.07
    ç½ijåĪĬ
    -0.07
     undermin
    -0.06
    yleft
    -0.06
    POSITIVE LOGITS
     sale
    0.08
     sold
    0.07
    -sale
    0.07
     auction
    0.07
     selling
    0.07
     SALE
    0.07
    -indent
    0.07
     pie
    0.07
     wr
    0.06
    åįĸ
    0.06
    Activations Density 0.011%

    No Known Activations