© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92854
    Prev
    Next
    INDEX
    Explanations

    phrases related to local geography and community involvement

    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
    rypton
    -0.08
    adar
    -0.07
     Fact
    -0.06
    atel
    -0.06
    olith
    -0.06
    æħİ
    -0.06
    uye
    -0.06
    atte
    -0.06
    ekil
    -0.06
     cha
    -0.06
    POSITIVE LOGITS
     area
    0.11
     city
    0.11
     local
    0.10
     region
    0.10
    local
    0.09
    city
    0.09
     town
    0.09
     área
    0.09
     ÑĢеги
    0.09
    region
    0.08
    Activations Density 0.025%

    No Known Activations