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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104554
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or roles associated with chaplains

    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
    -China
    -0.07
    esti
    -0.07
    atra
    -0.07
    eenth
    -0.07
    amente
    -0.07
    t
    -0.07
    Specifier
    -0.07
     Rahman
    -0.06
    pitch
    -0.06
    ãĤĥ
    -0.06
    POSITIVE LOGITS
    lain
    0.11
    oose
    0.08
    reuse
    0.07
    illus
    0.07
    urette
    0.06
    itos
    0.06
    -ves
    0.06
    .poly
    0.06
    ackages
    0.06
    è©
    0.06
    Activations Density 0.004%

    No Known Activations