© 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. 86057
    Prev
    Next
    INDEX
    Explanations

    references to victims and their relationships in crime-related 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
     BÃł
    -0.07
    CESS
    -0.07
    avin
    -0.07
     Respons
    -0.07
    adem
    -0.06
     Stats
    -0.06
    clair
    -0.06
    iew
    -0.06
    аÑĤоÑĢ
    -0.06
    -lang
    -0.06
    POSITIVE LOGITS
    orra
    0.07
     Marshall
    0.06
    loth
    0.06
     report
    0.06
    OrNil
    0.06
     Marshal
    0.06
     kontakt
    0.06
    à¸ŀà¸Ń
    0.06
    .report
    0.06
     cuckold
    0.06
    Activations Density 0.010%

    No Known Activations