© 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. 61550
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "whale" and its related forms

    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
    mund
    -0.08
    anmar
    -0.08
    oux
    -0.08
    ellite
    -0.08
    zzle
    -0.07
    ogue
    -0.07
    zos
    -0.07
    zet
    -0.07
    elman
    -0.07
    sel
    -0.07
    POSITIVE LOGITS
    bone
    0.07
    wright
    0.07
    ÙĨدÛĮ
    0.06
     passage
    0.06
    hound
    0.06
     Jennings
    0.06
    folio
    0.06
     passages
    0.06
     Gig
    0.06
    front
    0.06
    Activations Density 0.003%

    No Known Activations