© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63095
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort and hard work

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     IMM
    -0.06
    ald
    -0.06
    eya
    -0.06
    oha
    -0.06
     slack
    -0.06
    _lm
    -0.06
    dera
    -0.06
    ær
    -0.06
    ngo
    -0.06
    ervo
    -0.06
    POSITIVE LOGITS
     sacrific
    0.08
    .jsp
    0.08
    è¾Ľ
    0.07
     SAC
    0.07
    ÙĤد
    0.07
     risk
    0.06
     precious
    0.06
    acro
    0.06
     hard
    0.06
     risking
    0.06
    Activations Density 0.030%

    No Known Activations