© 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. 60094
    Prev
    Next
    INDEX
    Explanations

    references to immigration and its implications

    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
    inha
    -0.07
    roz
    -0.06
    ÙĪس
    -0.06
    ãĥ³ãĥIJ
    -0.06
    YLES
    -0.06
    rack
    -0.06
    รà¸ĩ
    -0.06
     Berm
    -0.06
    ceae
    -0.06
    ahi
    -0.06
    POSITIVE LOGITS
    ESCO
    0.07
    ICS
    0.07
    ÑĢÑĥд
    0.07
    ponsive
    0.07
    ifornia
    0.06
    gf
    0.06
    Ñıж
    0.06
    Mission
    0.06
    adio
    0.06
    IVO
    0.06
    Activations Density 0.021%

    No Known Activations