© 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. 41736
    Prev
    Next
    INDEX
    Explanations

    words related to deflection and diversion of attention or arguments

    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
    wan
    -0.07
    imen
    -0.06
    áºŃy
    -0.06
    çĩķ
    -0.06
    æĤ
    -0.06
    eniz
    -0.06
    imid
    -0.06
    wit
    -0.06
    VERTISEMENT
    -0.06
    wik
    -0.06
    POSITIVE LOGITS
     attention
    0.10
    attention
    0.10
     Attention
    0.09
     diverted
    0.09
     divert
    0.09
    Attention
    0.08
     deflect
    0.08
     khá»ıi
    0.08
     away
    0.08
     diversion
    0.07
    Activations Density 0.010%

    No Known Activations