© 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. 89596
    Prev
    Next
    INDEX
    Explanations

    terms related to particle interactions and impurity in models of condensed matter physics

    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
    annon
    -0.07
    omi
    -0.06
    rip
    -0.06
    elsey
    -0.06
    adores
    -0.06
     Floyd
    -0.06
    hra
    -0.06
    lant
    -0.06
    nell
    -0.06
    nan
    -0.06
    POSITIVE LOGITS
    åıĬåħ¶
    0.10
    èĩªèº«
    0.08
    EXPECT
    0.08
    essler
    0.08
     itself
    0.08
    #ac
    0.07
    #ad
    0.07
     Chandler
    0.07
    Chance
    0.07
    gil
    0.07
    Activations Density 0.107%

    No Known Activations