© 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. 87497
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or confrontation in political 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
    ODO
    -0.07
     lé
    -0.07
    essenger
    -0.07
    Ø®ÙĬ
    -0.07
     سÙģ
    -0.06
    ovi
    -0.06
    еÑĢи
    -0.06
    ovie
    -0.06
    akis
    -0.06
     svob
    -0.06
    POSITIVE LOGITS
     floor
    0.09
    Floor
    0.08
     Floor
    0.08
     motions
    0.08
     session
    0.07
     motion
    0.07
     recess
    0.07
    floor
    0.07
     dramatic
    0.07
     procedural
    0.07
    Activations Density 0.012%

    No Known Activations