© 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. 116593
    Prev
    Next
    INDEX
    Explanations

    phrases indicating shocking or unusual events

    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
    .SDK
    -0.08
    alue
    -0.07
    à¥įसर
    -0.07
    ãĤĵãģ©
    -0.07
    estre
    -0.07
     Kaynak
    -0.07
    ãĥĥãĤ°
    -0.07
    aley
    -0.07
    ieu
    -0.07
    _roi
    -0.07
    POSITIVE LOGITS
     someone
    0.07
     woman
    0.06
     CIS
    0.06
    abee
    0.06
    lege
    0.06
    leDb
    0.05
     giant
    0.05
     oblig
    0.05
     Lore
    0.05
     lady
    0.05
    Activations Density 0.019%

    No Known Activations