© 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 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. 85783
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in education or public service

    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
     Albuquerque
    -0.10
     Auckland
    -0.10
    yonel
    -0.08
     Idaho
    -0.08
     Utah
    -0.08
    izona
    -0.08
     BYU
    -0.08
    .nz
    -0.08
     Manit
    -0.08
     Rockies
    -0.07
    POSITIVE LOGITS
     Maryland
    0.25
     Baltimore
    0.24
     Orioles
    0.18
    altimore
    0.17
     Ches
    0.16
     Md
    0.14
     mary
    0.12
    Mary
    0.12
     Bethesda
    0.12
    Md
    0.11
    Activations Density 0.135%

    No Known Activations