© 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. 96304
    Prev
    Next
    INDEX
    Explanations

    terms related to leadership roles and affiliations

    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
    iaux
    -0.08
    /antlr
    -0.07
    plements
    -0.07
    sea
    -0.07
    664
    -0.07
    楽
    -0.07
    activex
    -0.07
    ventus
    -0.06
    Vtbl
    -0.06
    oppel
    -0.06
    POSITIVE LOGITS
    chet
    0.08
    undy
    0.07
    ing
    0.06
     Ken
    0.06
     Nou
    0.06
    -many
    0.06
     hearing
    0.06
    poÄįet
    0.05
    vg
    0.05
    arily
    0.05
    Activations Density 0.033%

    No Known Activations