© 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. 116582
    Prev
    Next
    INDEX
    Explanations

    words related to mentorship and guidance

    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
    lette
    -0.10
    ATCH
    -0.08
    keit
    -0.08
    VERTISE
    -0.08
    IXEL
    -0.07
    cts
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    letic
    -0.07
    ritten
    -0.07
    ât
    -0.07
    POSITIVE LOGITS
    ally
    0.10
    tle
    0.07
    ALLY
    0.07
     Ally
    0.07
    ertainment
    0.06
    ys
    0.06
    ropp
    0.06
    earn
    0.06
    ening
    0.06
    ear
    0.06
    Activations Density 0.003%

    No Known Activations