© 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. 92098
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and themes of transatlantic connections

    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
    rych
    -0.07
    cion
    -0.06
    ãģ¤ãģ¶
    -0.06
     Ray
    -0.06
     Nav
    -0.06
    ugu
    -0.06
     Esper
    -0.06
     ag
    -0.05
     perc
    -0.05
    ndo
    -0.05
    POSITIVE LOGITS
     overseas
    0.14
     Europe
    0.13
     abroad
    0.11
    Europe
    0.11
     ÐķвÑĢоп
    0.11
     European
    0.10
     europé
    0.10
    urope
    0.10
     foreign
    0.10
     europe
    0.10
    Activations Density 0.068%

    No Known Activations