© 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. 14146
    Prev
    Next
    INDEX
    Explanations

    specific locations or landmarks associated with 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
     Dallas
    -0.07
     Texas
    -0.07
    .synthetic
    -0.07
    monton
    -0.07
     Kansas
    -0.07
     IBM
    -0.07
     Manhattan
    -0.06
     Cincinnati
    -0.06
    angi
    -0.06
     Ohio
    -0.06
    POSITIVE LOGITS
     Cornwall
    0.14
     Portland
    0.14
    Portland
    0.13
     Maine
    0.10
     Plymouth
    0.10
     Kerala
    0.10
     Corn
    0.08
     Devon
    0.08
     Oregon
    0.07
    Oregon
    0.07
    Activations Density 0.053%

    No Known Activations