© 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. 38250
    Prev
    Next
    INDEX
    Explanations

    references to social structures and dynamics

    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
    avra
    -0.09
    assin
    -0.08
    eshire
    -0.06
    onto
    -0.06
     Dann
    -0.06
    inoa
    -0.06
    irit
    -0.06
    ело
    -0.06
    सन
    -0.06
    FormsModule
    -0.06
    POSITIVE LOGITS
     differently
    0.10
     sebagai
    0.07
    hol
    0.07
     как
    0.07
     hol
    0.07
     jako
    0.07
    ials
    0.07
    /MPL
    0.07
    à¹ĥà¸Ļร
    0.07
     ë°ĶëĿ¼
    0.07
    Activations Density 0.026%

    No Known Activations