© 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. 17-LLAMASCOPE-RES-131K
    6. 60423
    Prev
    Next
    INDEX
    Explanations

    phrases indicating human experiences and relationships

    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
    aybe
    -0.09
    .sul
    -0.09
    ertino
    -0.09
    abee
    -0.09
    abbo
    -0.09
    ॰
    -0.08
    że
    -0.08
     Ekon
    -0.08
    彡
    -0.08
    IFn
    -0.08
    POSITIVE LOGITS
    uran
    0.06
    zd
    0.06
     S
    0.06
     D
    0.06
     Parker
    0.06
     Bald
    0.05
     St
    0.05
    uit
    0.05
     .↵
    0.05
    âĢIJ
    0.05
    Activations Density 0.037%

    No Known Activations