© 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. 57882
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions and expressions of skepticism

    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
    raman
    -0.07
    esub
    -0.07
    ands
    -0.07
     IonicPage
    -0.06
    emale
    -0.06
    ãĤ
    -0.06
     æķħ
    -0.06
    amax
    -0.06
     hypo
    -0.06
    avenport
    -0.06
    POSITIVE LOGITS
     synonym
    0.06
    herits
    0.06
     haven
    0.06
    تÙĪر
    0.06
    izm
    0.06
     Haven
    0.06
     mai
    0.06
     hadn
    0.06
    uve
    0.06
    zza
    0.06
    Activations Density 0.027%

    No Known Activations