© 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. 5856
    Prev
    Next
    INDEX
    Explanations

    terms related to social dynamics and interpersonal relationships

    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
    ors
    -0.07
    ners
    -0.07
    gers
    -0.06
     itself
    -0.06
    ,
    -0.06
     Ham
    -0.06
    nes
    -0.06
     blah
    -0.06
     doing
    -0.06
     animated
    -0.05
    POSITIVE LOGITS
    ê»
    0.08
    OutOfRange
    0.08
     ìĤ¬íķŃ
    0.07
    ÑĢÑİ
    0.07
    --------------------------------------------------------------------------↵
    0.07
     ìĹŃìĭľ
    0.07
    ãģĵãģĿ
    0.07
    izabeth
    0.07
    Https
    0.07
     Ùħسئ
    0.07
    Activations Density 0.049%

    No Known Activations