© 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. 89715
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" that connect family 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
    orre
    -0.07
    âu
    -0.07
    ivot
    -0.07
    ifiable
    -0.07
    orrar
    -0.06
    arda
    -0.06
    rais
    -0.06
    opak
    -0.06
    OptionsResolver
    -0.06
     Gardner
    -0.06
    POSITIVE LOGITS
     zwar
    0.07
    ÄĽtÃŃ
    0.06
     its
    0.06
    /or
    0.06
    thouse
    0.06
    ãĥ©ãĥ³ãĥī
    0.06
    ropolis
    0.06
    obar
    0.06
     Hasan
    0.06
    ylan
    0.05
    Activations Density 0.001%

    No Known Activations