© 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. 14175
    Prev
    Next
    INDEX
    Explanations

    terms related to searching or queries

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ,
    -0.07
    YZ
    -0.06
    acha
    -0.06
    769
    -0.06
    agh
    -0.06
    acre
    -0.06
    fromJson
    -0.06
    rior
    -0.06
     (
    -0.06
    iginal
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    cono
    0.08
     engine
    0.07
    emain
    0.07
     engines
    0.07
    lights
    0.07
    StringEncoding
    0.07
    ê·¹
    0.07
     Engines
    0.07
    asted
    0.07
    Activations Density 0.007%

    No Known Activations