© 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. 42531
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive adjectives related to individuals and groups

    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
     proh
    -0.08
    ussen
    -0.08
    ãĤ«ãĥ¼
    -0.07
    apons
    -0.07
    owell
    -0.07
    uyên
    -0.07
    unma
    -0.07
     Ekon
    -0.07
    ayd
    -0.07
    obo
    -0.07
    POSITIVE LOGITS
     counterparts
    0.12
     counterpart
    0.11
     correspond
    0.06
     predecessors
    0.06
     Lomb
    0.06
     Seymour
    0.06
     mold
    0.05
     peers
    0.05
     colleagues
    0.05
     opposite
    0.05
    Activations Density 0.006%

    No Known Activations