© 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. 126502
    Prev
    Next
    INDEX
    Explanations

    instances of the word "overly" and its variations, indicating excessive or exaggerated qualities

    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
     Falcon
    -0.06
     deepest
    -0.06
     (__
    -0.06
    iname
    -0.06
    amework
    -0.06
     front
    -0.06
    ibli
    -0.06
     оÑĤп
    -0.06
     Caller
    -0.06
    payload
    -0.06
    POSITIVE LOGITS
    nda
    0.08
    ussy
    0.07
    ehir
    0.07
    FLT
    0.07
    vier
    0.07
    ÑıÑħ
    0.07
    -special
    0.07
    ahat
    0.07
    AGR
    0.07
    acent
    0.07
    Activations Density 0.005%

    No Known Activations