© 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. 71769
    Prev
    Next
    INDEX
    Explanations

    details about fashion items and their characteristics

    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
     s
    -0.06
    uer
    -0.06
     pap
    -0.06
     Ñħол
    -0.06
    ingleton
    -0.06
     thr
    -0.06
     confl
    -0.06
     reg
    -0.05
    ↵
    -0.05
    gos
    -0.05
    POSITIVE LOGITS
    ÄĽt
    0.07
    eydi
    0.07
    eniz
    0.07
    STM
    0.07
    NavItem
    0.07
    áte
    0.07
     caÅĤ
    0.07
    olet
    0.07
    .appspot
    0.07
    мини
    0.06
    Activations Density 0.028%

    No Known Activations