© 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. 124573
    Prev
    Next
    INDEX
    Explanations

    directional words and positions

    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
     arada
    -0.09
    ýt
    -0.08
    (::
    -0.08
    InSection
    -0.07
    ả
    -0.07
    egie
    -0.07
    .chk
    -0.07
    .addObject
    -0.07
    ements
    -0.07
    leta
    -0.07
    POSITIVE LOGITS
    ICC
    0.06
     progress
    0.06
     Progress
    0.06
     ,
    0.06
    most
    0.06
    meli
    0.06
     Blasio
    0.05
    ett
    0.05
    iar
    0.05
     left
    0.05
    Activations Density 0.005%

    No Known Activations