© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27180
    Prev
    Next
    INDEX
    Explanations

    references to political actions and sanctions

    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
     Compliance
    -0.07
    ÑĥÑĢн
    -0.07
    ADI
    -0.06
    глÑı
    -0.06
     Hess
    -0.06
    avou
    -0.06
    .gwt
    -0.06
     Chest
    -0.06
    ibar
    -0.06
     Guerr
    -0.06
    POSITIVE LOGITS
     Foreign
    0.07
    olen
    0.07
    RetVal
    0.07
    Foreign
    0.07
     attribution
    0.06
     foreign
    0.06
     cyber
    0.06
    oling
    0.06
    .Fore
    0.06
    -src
    0.06
    Activations Density 0.011%

    No Known Activations