© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85221
    Prev
    Next
    INDEX
    Explanations

    aspects of family history and relationships

    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
    neum
    -0.07
     Cousins
    -0.07
    eldom
    -0.06
    riend
    -0.06
    roi
    -0.06
     Teens
    -0.06
    YZ
    -0.06
    esterday
    -0.06
     Mour
    -0.06
    mdb
    -0.06
    POSITIVE LOGITS
    .hxx
    0.06
     remar
    0.06
     AUTHORS
    0.06
    gregation
    0.06
    quate
    0.06
    uerdo
    0.06
    éĶ
    0.06
    çĮ
    0.06
    _BINDING
    0.06
    åĭ¤
    0.06
    Activations Density 0.025%

    No Known Activations