© 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. 17-LLAMASCOPE-RES-131K
    11. 70883
    Prev
    Next
    INDEX
    Explanations

    references to conflict zones and territorial control

    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
    trak
    -0.06
    ÑĨÑĸ
    -0.06
     withStyles
    -0.06
    ãĥ«ãĥī
    -0.06
    eza
    -0.06
     Solomon
    -0.06
    @nate
    -0.06
     Leak
    -0.06
     Socialist
    -0.06
    oir
    -0.05
    POSITIVE LOGITS
    å¥Ķ
    0.07
    sy
    0.06
     control
    0.06
    ActionCreators
    0.06
    .LoggerFactory
    0.06
    /controllers
    0.06
    ilent
    0.06
    Transactional
    0.06
    .Networking
    0.06
    /controller
    0.06
    Activations Density 0.021%

    No Known Activations