© 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. 17-LLAMASCOPE-RES-131K
    11. 59835
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one" and other references to individual people or subjective opinions

    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
    otime
    -0.09
    .fromFunction
    -0.08
    .builders
    -0.08
    loff
    -0.08
    Reporter
    -0.08
    istrovstvÃŃ
    -0.08
    GuidId
    -0.08
    borough
    -0.07
    .updateDynamic
    -0.07
    ICO
    -0.07
    POSITIVE LOGITS
     participant
    0.08
     muse
    0.07
     recent
    0.06
     anon
    0.06
     of
    0.06
    Mrs
    0.06
     man
    0.06
    opa
    0.06
     contemporary
    0.06
    Âł
    0.05
    Activations Density 0.005%

    No Known Activations