© 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. 53854
    Prev
    Next
    INDEX
    Explanations

    words related to importance and importation

    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
    inders
    -0.07
    ÑĩаÑģ
    -0.07
    anders
    -0.07
    unden
    -0.07
    ॰
    -0.07
    :CGRect
    -0.06
    stoup
    -0.06
    ÐļТ
    -0.06
    istra
    -0.06
    _Lean
    -0.06
    POSITIVE LOGITS
    ation
    0.10
    ance
    0.09
    ed
    0.09
    ated
    0.08
    ar
    0.07
    unate
    0.07
    ing
    0.07
    er
    0.07
    a
    0.07
    aight
    0.07
    Activations Density 0.014%

    No Known Activations