© 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. 9-LLAMASCOPE-RES-131K
    11. 96244
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizations and their roles in various contexts

    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
    ÑĢек
    -0.07
    337
    -0.07
     kat
    -0.07
    ýn
    -0.07
    çıŃ
    -0.07
    insn
    -0.06
    ãģĺ
    -0.06
    оÑĥ
    -0.06
    ork
    -0.06
    chia
    -0.06
    POSITIVE LOGITS
     abbreviated
    0.08
    glich
    0.06
     (
    0.06
    gres
    0.06
    acker
    0.06
     Artem
    0.06
     Hood
    0.06
    ãĤ´ãĥª
    0.06
    dac
    0.06
    .escape
    0.06
    Activations Density 0.599%

    No Known Activations