© 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. 91740
    Prev
    Next
    INDEX
    Explanations

    phrases related to familial relationships and connections

    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
    chez
    -0.07
    /dialog
    -0.07
    avec
    -0.07
    ivec
    -0.07
    olini
    -0.07
     ÑĥÑĤ
    -0.07
    351
    -0.06
    _$_
    -0.06
    YW
    -0.06
    inja
    -0.06
    POSITIVE LOGITS
    ephy
    0.06
     purpose
    0.06
    endet
    0.06
     greatness
    0.06
    ulas
    0.06
    uther
    0.06
    ested
    0.05
    inqu
    0.05
    æĬĺ
    0.05
     bro
    0.05
    Activations Density 0.009%

    No Known Activations