© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90602
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and family values

    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
    å±¥
    -0.07
    ãĤ¢ãĥ¼
    -0.07
    ähr
    -0.07
    EGA
    -0.07
     kosten
    -0.06
    eten
    -0.06
    blr
    -0.06
     mej
    -0.06
    laden
    -0.06
    mail
    -0.06
    POSITIVE LOGITS
     lifestyle
    0.07
     freedom
    0.07
    unta
    0.07
    iska
    0.06
     FORE
    0.06
     income
    0.06
    ä½
    0.06
    apers
    0.06
     passive
    0.06
    ľ
    0.06
    Activations Density 0.011%

    No Known Activations