© 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. 63295
    Prev
    Next
    INDEX
    Explanations

    terminology related to formal organizational structures and roles

    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
     drunk
    -0.07
     Santana
    -0.06
     Samantha
    -0.06
     Yahoo
    -0.06
     Millennium
    -0.06
     poor
    -0.06
    181
    -0.06
     somebody
    -0.06
     extraordinary
    -0.06
     Martial
    -0.05
    POSITIVE LOGITS
    Mess
    0.09
    izr
    0.08
    pleted
    0.08
    Ģ
    0.08
    izedName
    0.08
    rypton
    0.08
    лага
    0.07
    BackPressed
    0.07
    outine
    0.07
    TOTYPE
    0.07
    Activations Density 0.007%

    No Known Activations