© 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. 80877
    Prev
    Next
    INDEX
    Explanations

    references to rural areas and associated policies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ooter
    -0.07
    endl
    -0.07
    tsky
    -0.06
    iniz
    -0.06
    chsel
    -0.06
    adÃŃ
    -0.06
    elloworld
    -0.06
    	volatile
    -0.06
    ttp
    -0.06
    γγελ
    -0.06
    POSITIVE LOGITS
    amen
    0.08
     urban
    0.08
    urban
    0.07
     Urban
    0.07
     Hab
    0.06
    allon
    0.06
    741
    0.06
    /stdc
    0.06
    TestCategory
    0.06
     SON
    0.06
    Activations Density 0.000%

    No Known Activations