© 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. 15-LLAMASCOPE-RES-131K
    11. 596
    Prev
    Next
    INDEX
    Explanations

    references to the ages of children

    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
    abant
    -0.07
    afil
    -0.07
    udic
    -0.07
    éis
    -0.07
     молод
    -0.07
    assel
    -0.07
    undry
    -0.06
    tape
    -0.06
    atted
    -0.06
    otype
    -0.06
    POSITIVE LOGITS
     children
    0.07
    (children
    0.07
     latency
    0.06
    rend
    0.06
    tern
    0.06
    children
    0.06
    enheim
    0.06
    AAAA
    0.06
    rou
    0.06
    reen
    0.06
    Activations Density 0.021%

    No Known Activations