© 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. 9-LLAMASCOPE-RES-131K
    11. 96287
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics related to company rankings and performance

    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
    alem
    -0.08
    uset
    -0.07
    elman
    -0.07
    argo
    -0.07
     Amerikan
    -0.07
    .idea
    -0.07
    eldorf
    -0.07
    hev
    -0.06
     Erotik
    -0.06
    REAM
    -0.06
    POSITIVE LOGITS
    Insn
    0.07
    rog
    0.07
    rompt
    0.06
     Cooler
    0.06
     quantum
    0.06
    utin
    0.06
    اÙĨÙĩ
    0.06
     баб
    0.06
    arna
    0.06
     dads
    0.06
    Activations Density 0.001%

    No Known Activations