© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97578
    Prev
    Next
    INDEX
    Explanations

    references to animal cruelty and unethical treatment of animals

    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
     æ©Ł
    -0.08
    بÙĪاسطة
    -0.08
    rrha
    -0.08
    ãĥĭãĤ¢
    -0.08
    ello
    -0.08
    assin
    -0.07
    GenerationStrategy
    -0.07
     Äijá»ĵng
    -0.07
    igner
    -0.07
    thon
    -0.07
    POSITIVE LOGITS
     (
    0.06
    otos
    0.06
     Hollywood
    0.06
    arro
    0.05
     end
    0.05
    -
    0.05
     yard
    0.05
    ,
    0.05
     in
    0.05
     do
    0.05
    Activations Density 0.016%

    No Known Activations