© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 97183
    Prev
    Next
    INDEX
    Explanations

    expressions of absurdity or extreme exaggeration

    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
    inst
    -0.07
    etik
    -0.06
    bie
    -0.06
    aliz
    -0.06
    lots
    -0.06
    anken
    -0.06
    egra
    -0.06
    oom
    -0.06
     Ara
    -0.06
    ÅĻÃŃ
    -0.06
    POSITIVE LOGITS
    -looking
    0.09
    naire
    0.08
    ously
    0.07
    Spo
    0.07
    _svc
    0.07
    mente
    0.07
     amount
    0.07
    idad
    0.07
    NESS
    0.07
    roulette
    0.07
    Activations Density 0.014%

    No Known Activations