© 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. 61337
    Prev
    Next
    INDEX
    Explanations

    names of family members and relatives

    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
    unei
    -0.07
    اذ
    -0.07
    Configurer
    -0.07
    .onOptionsItemSelected
    -0.07
    fffffff
    -0.07
    (IServiceCollection
    -0.07
    RelativeTo
    -0.07
    ServiceProvider
    -0.06
     addCriterion
    -0.06
    (disposing
    -0.06
    POSITIVE LOGITS
    lus
    0.07
    &nbsp
    0.06
    ãĢģ
    0.06
    iasi
    0.06
    wind
    0.06
    aiser
    0.06
    Ĩ
    0.06
     wes
    0.05
     Mik
    0.05
    ÑīеÑģÑĤво
    0.05
    Activations Density 0.005%

    No Known Activations