© 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. 39971
    Prev
    Next
    INDEX
    Explanations

    fabrics and textiles used in clothing and home decor

    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
    eut
    -0.07
    ̧
    -0.06
    åı«
    -0.06
    er
    -0.06
    naments
    -0.06
     glasses
    -0.06
    nga
    -0.06
     Gil
    -0.06
    e
    -0.06
     Lit
    -0.06
    POSITIVE LOGITS
    -covered
    0.08
    -lined
    0.08
    oucher
    0.07
    -like
    0.07
    -text
    0.07
    éru
    0.07
    /text
    0.07
    GINE
    0.07
    ÑĥлÑı
    0.07
    å¼µ
    0.07
    Activations Density 0.016%

    No Known Activations