© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69329
    Prev
    Next
    INDEX
    Explanations

    URLs and links to online content

    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
    wa
    -0.06
    anko
    -0.06
     Vital
    -0.05
    raz
    -0.05
    606
    -0.05
    ude
    -0.05
     hazard
    -0.05
    ett
    -0.05
     Ban
    -0.05
    .warn
    -0.05
    POSITIVE LOGITS
    SAME
    0.08
    arLayout
    0.08
    Ŀ¼
    0.07
    onne
    0.07
    åĽ
    0.07
    εÏį
    0.07
     ===>
    0.07
    ito
    0.07
     IonicModule
    0.07
    addtogroup
    0.07
    Activations Density 0.001%

    No Known Activations