© 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 EvalsExportsinterp-engineNEWAPI 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. 70220
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the act of taking control or possession of something

    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
    rev
    -0.09
    sh
    -0.07
    ting
    -0.07
    ersistence
    -0.07
    inez
    -0.07
    ness
    -0.07
    rem
    -0.07
    ning
    -0.07
    isé
    -0.07
    Ä«
    -0.06
    POSITIVE LOGITS
    stakes
    0.09
    RIPT
    0.08
    ibold
    0.08
    ç¶ļ
    0.08
    иденÑĤ
    0.07
    ingly
    0.07
    uhl
    0.07
    hold
    0.07
    adlo
    0.07
    ĶåĽŀ
    0.07
    Activations Density 0.007%

    No Known Activations