© 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. 17-LLAMASCOPE-RES-131K
    11. 17337
    Prev
    Next
    INDEX
    Explanations

    references to political control and territorial conflicts

    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
    illard
    -0.07
    ukan
    -0.07
     Fra
    -0.06
     Gill
    -0.06
    /Instruction
    -0.06
     Burk
    -0.06
     Eld
    -0.06
    ubb
    -0.06
    _ptr
    -0.06
    lington
    -0.06
    POSITIVE LOGITS
     intellig
    0.07
    Wunused
    0.07
     rewind
    0.07
     souÄįást
    0.07
    Partition
    0.07
    partition
    0.07
     pog
    0.07
     MÃ¼ÅŁ
    0.07
    ê°IJ
    0.07
    apore
    0.06
    Activations Density 0.041%

    No Known Activations