© 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. 18485
    Prev
    Next
    INDEX
    Explanations

    references to care and concern for loved ones or family members

    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
    arten
    -0.08
    mÃŃ
    -0.08
    ">//
    -0.07
    ezi
    -0.07
    梨
    -0.07
    uma
    -0.07
    itest
    -0.07
    icast
    -0.07
    ctal
    -0.07
    ORA
    -0.07
    POSITIVE LOGITS
     loved
    0.19
     Loved
    0.15
     someone
    0.13
     somebody
    0.12
    someone
    0.11
     friend
    0.11
     friends
    0.10
    Someone
    0.10
     relatives
    0.10
     Someone
    0.09
    Activations Density 0.122%

    No Known Activations