© 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. 9-LLAMASCOPE-RES-131K
    11. 99193
    Prev
    Next
    INDEX
    Explanations

    phrases related to third parties and privacy concerns

    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
    izio
    -0.07
     Gim
    -0.06
    jam
    -0.06
    acer
    -0.06
     Narrative
    -0.06
     Sür
    -0.06
    vert
    -0.06
     sav
    -0.06
     Mum
    -0.06
    peed
    -0.06
    POSITIVE LOGITS
    lal
    0.08
    inson
    0.07
    ropolis
    0.07
    anova
    0.06
    976
    0.06
    oyo
    0.06
    ingham
    0.06
     Karlov
    0.06
     defaultManager
    0.06
    iton
    0.06
    Activations Density 0.000%

    No Known Activations