© 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. 72508
    Prev
    Next
    INDEX
    Explanations

    instances of the word "doing" and related phrases about actions or intentions

    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
    obao
    -0.08
    ining
    -0.07
    asa
    -0.07
     dem
    -0.06
    resco
    -0.06
    ogi
    -0.06
    uko
    -0.06
    wards
    -0.06
    ActionCreators
    -0.06
    lic
    -0.06
    POSITIVE LOGITS
    ector
    0.08
     Kelley
    0.06
    hee
    0.06
     Why
    0.06
    297
    0.06
    ideo
    0.06
    ázev
    0.06
    uteÄį
    0.06
    Why
    0.06
    νÏī
    0.06
    Activations Density 0.005%

    No Known Activations