© 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. 70676
    Prev
    Next
    INDEX
    Explanations

    expressions of superiority or preference

    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
    verbatim
    -0.06
    ulong
    -0.06
    pard
    -0.06
    taire
    -0.06
    ius
    -0.06
    vala
    -0.06
    ÑĪев
    -0.06
    ifax
    -0.06
     Fro
    -0.06
    tright
    -0.06
    POSITIVE LOGITS
     way
    0.12
     place
    0.10
     reason
    0.09
     ways
    0.08
     façon
    0.07
    .way
    0.07
     thing
    0.07
     WAY
    0.07
    place
    0.07
     Way
    0.07
    Activations Density 0.004%

    No Known Activations