© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16348
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and locations

    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
    âĢ¦↵↵↵
    -0.08
    usta
    -0.06
    *)((
    -0.06
    anela
    -0.06
    ção
    -0.06
    wares
    -0.05
    ر
    -0.05
    312
    -0.05
    ken
    -0.05
    кеÑĤ
    -0.05
    POSITIVE LOGITS
    UNET
    0.07
    antz
    0.06
     rem
    0.06
    Ñįй
    0.06
    ÑħодиÑĤÑĮ
    0.06
    MESS
    0.06
    tsky
    0.06
    âĻª
    0.06
    orn
    0.06
     explos
    0.06
    Activations Density 0.085%

    No Known Activations