© 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. 15-LLAMASCOPE-RES-131K
    11. 88489
    Prev
    Next
    INDEX
    Explanations

    organizational names and titles related to various sectors

    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
    ohana
    -0.09
     STDCALL
    -0.07
    еÑĩ
    -0.07
     вÑģÑı
    -0.07
    Streamer
    -0.07
    omat
    -0.07
    enek
    -0.07
    enville
    -0.07
    aska
    -0.07
    hya
    -0.07
    POSITIVE LOGITS
     chief
    0.07
     president
    0.06
    idos
    0.06
    éĹ
    0.06
     integr
    0.06
     mes
    0.06
     intern
    0.06
     backed
    0.05
     terminal
    0.05
     обÑĭ
    0.05
    Activations Density 0.020%

    No Known Activations