© 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. 94291
    Prev
    Next
    INDEX
    Explanations

    question marks that indicate inquiries or uncertainties

    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
    geber
    -0.08
    pek
    -0.07
    beg
    -0.07
    erial
    -0.06
    ight
    -0.06
    swire
    -0.06
    170
    -0.06
    atz
    -0.06
    wil
    -0.06
    åIJ¦
    -0.06
    POSITIVE LOGITS
    ève
    0.07
    REATE
    0.07
    SystemService
    0.06
     mam
    0.06
    ÏģεÏĤ
    0.06
    RTL
    0.06
    PU
    0.06
    à¤ĺ
    0.06
    ÏĥÏħ
    0.06
     Horny
    0.06
    Activations Density 0.009%

    No Known Activations