© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5880
    Prev
    Next
    INDEX
    Explanations

    instances of the word "its"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    his
    -0.07
    hip
    -0.07
    çļĦåľ°æĸ¹
    -0.07
     sobÄĽ
    -0.07
     Chapman
    -0.07
    713
    -0.07
     themselves
    -0.07
    ERY
    -0.06
    orks
    -0.06
    erin
    -0.06
    POSITIVE LOGITS
     itself
    0.15
     own
    0.13
    lef
    0.12
    iner
    0.12
     its
    0.09
    _own
    0.09
    own
    0.09
    zik
    0.09
     Its
    0.08
    panic
    0.08
    Activations Density 0.098%

    No Known Activations