© 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. 82478
    Prev
    Next
    INDEX
    Explanations

    topics related to trends and changes in societal or economic circumstances

    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
    uyla
    -0.07
    frauen
    -0.07
    ivant
    -0.07
    ulle
    -0.07
     Byl
    -0.07
    /MPL
    -0.07
     salope
    -0.06
     Sexe
    -0.06
     mastur
    -0.06
    اÙħÛĮÙĨ
    -0.06
    POSITIVE LOGITS
     top
    0.07
    EDIUM
    0.07
     counties
    0.06
     buckets
    0.06
    rawn
    0.06
     absol
    0.06
     bast
    0.06
     score
    0.06
    iaux
    0.06
    Pair
    0.06
    Activations Density 0.012%

    No Known Activations