© 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. 107907
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to hopes, ambitions, and desires

    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
    spiel
    -0.09
     Mour
    -0.07
    essa
    -0.07
    ddy
    -0.07
    nee
    -0.07
    ery
    -0.06
    marks
    -0.06
    men
    -0.06
    -Apr
    -0.06
    erson
    -0.06
    POSITIVE LOGITS
    ptions
    0.07
    ibo
    0.07
    /target
    0.07
     Seek
    0.07
     greatness
    0.07
    äºİ
    0.07
    .getOwnProperty
    0.07
    æĸ¼
    0.07
     ApiController
    0.06
    LIK
    0.06
    Activations Density 0.002%

    No Known Activations