© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89721
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical interactions and body positioning

    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
    ifferential
    -0.06
    zew
    -0.06
    abant
    -0.06
    gili
    -0.06
    ephir
    -0.06
    mana
    -0.06
    estring
    -0.06
    relude
    -0.06
    chet
    -0.06
    zi
    -0.06
    POSITIVE LOGITS
    å¼ı
    0.07
     Neville
    0.07
    ASSES
    0.06
    tures
    0.06
    ãģ¾ãģ¾
    0.06
    bid
    0.06
    çı
    0.06
    ight
    0.06
    aturas
    0.06
    @(
    0.06
    Activations Density 0.013%

    No Known Activations