© 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 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. 130735
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases related to travel authorization and regulations

    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
    tah
    -0.08
    UILayout
    -0.07
    bote
    -0.07
    olls
    -0.07
    .inf
    -0.07
     Petr
    -0.07
    èĮĤ
    -0.07
    967
    -0.07
    奴
    -0.07
    anchor
    -0.07
    POSITIVE LOGITS
     Belgian
    0.18
     Belgium
    0.17
     Brussels
    0.16
     Belg
    0.15
     Flem
    0.15
     belg
    0.13
     Cincinnati
    0.10
     Bengals
    0.10
     Gh
    0.09
     Luxembourg
    0.09
    Activations Density 0.087%

    No Known Activations