© 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. 75087
    Prev
    Next
    INDEX
    Explanations

    terms related to selling or market transactions

    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
    riel
    -0.07
    zÃŃ
    -0.07
    anh
    -0.06
     Coch
    -0.06
    ÅĤo
    -0.06
    лиÑĨ
    -0.06
    -scalable
    -0.05
     Fade
    -0.05
    ysa
    -0.05
    ¹Ħ
    -0.05
    POSITIVE LOGITS
    erm
    0.09
    rice
    0.08
    ings
    0.08
    ars
    0.07
    otten
    0.07
    toy
    0.07
    erten
    0.07
    upplier
    0.07
    enn
    0.07
    gro
    0.07
    Activations Density 0.006%

    No Known Activations