© 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. 17-LLAMASCOPE-RES-131K
    11. 60961
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases emphasizing uniqueness or exclusivity

    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
    ishly
    -0.07
    ë¡Ģ
    -0.07
    tere
    -0.07
    actly
    -0.07
    з
    -0.07
    _simps
    -0.06
    AdapterFactory
    -0.06
    istor
    -0.06
    871
    -0.06
    opic
    -0.06
    POSITIVE LOGITS
     thing
    0.13
     way
    0.09
     Thing
    0.08
     reason
    0.08
    thing
    0.08
     other
    0.08
    .way
    0.07
     difference
    0.07
     truly
    0.07
    (thing
    0.07
    Activations Density 0.008%

    No Known Activations