© 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 EvalsExportsinterp-engineNEWAPI 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. 120561
    Prev
    Next
    INDEX
    Explanations

    instances of quotations and specific referencing formats in the text

    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
    ndon
    -0.08
    plx
    -0.07
    orge
    -0.07
    ULAR
    -0.07
    agine
    -0.07
    ilar
    -0.07
    олÑİ
    -0.07
    кÑĥп
    -0.07
    nga
    -0.07
    аÑĢÑĩ
    -0.07
    POSITIVE LOGITS
     Seven
    0.06
    ãĤīãģĹãģĦ
    0.06
    ÂĢÂ
    0.06
     Sevent
    0.05
     ÃĶ
    0.05
     âĢŀ
    0.05
     Kramer
    0.05
     Hammer
    0.05
     »
    0.05
    iare
    0.05
    Activations Density 0.024%

    No Known Activations