© 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. 108618
    Prev
    Next
    INDEX
    Explanations

    emotional interactions between characters

    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
     whistle
    -0.06
    tern
    -0.06
    ç¯ĩ
    -0.06
    istor
    -0.06
     Realty
    -0.06
     "
    -0.06
    ẩu
    -0.05
    Cancellation
    -0.05
     sou
    -0.05
    UINT
    -0.05
    POSITIVE LOGITS
    icha
    0.07
    íĨłíĨł
    0.07
    imson
    0.07
    оÑģÑĮ
    0.07
     gian
    0.07
    egal
    0.07
    žÃŃt
    0.07
     Leer
    0.07
    ê¸
    0.07
    rror
    0.07
    Activations Density 0.032%

    No Known Activations