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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74279
    Prev
    Next
    INDEX
    Explanations

    locations that are part of a geographical context

    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
    legate
    -0.07
     aliqua
    -0.07
    anzeigen
    -0.07
    vala
    -0.07
    criptor
    -0.07
    ;element
    -0.07
     pij
    -0.07
    pus
    -0.06
    utenberg
    -0.06
    odie
    -0.06
    POSITIVE LOGITS
    erot
    0.07
     ranging
    0.07
     simple
    0.06
     unto
    0.06
    enco
    0.06
     Vul
    0.06
    itters
    0.06
     Simple
    0.06
     Vit
    0.06
    oen
    0.06
    Activations Density 0.028%

    No Known Activations