© 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. 121304
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal history

    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
    etti
    -0.08
    erti
    -0.07
    qx
    -0.06
    arshal
    -0.06
    chema
    -0.06
    tent
    -0.06
    slaught
    -0.06
     odkazy
    -0.06
    webtoken
    -0.06
    .sponge
    -0.06
    POSITIVE LOGITS
     famously
    0.08
     reportedly
    0.07
     notoriously
    0.07
     ur
    0.07
     refused
    0.06
    ENA
    0.06
     contemporary
    0.06
     (!
    0.06
    642
    0.06
     literally
    0.06
    Activations Density 0.094%

    No Known Activations