© 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. 116734
    Prev
    Next
    INDEX
    Explanations

    elements of comparison and personal opinion

    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
    enco
    -0.09
    lád
    -0.08
    oplay
    -0.08
    æĹıèĩªæ²»
    -0.07
    ůst
    -0.07
    اÙģÛĮ
    -0.07
    ROTO
    -0.07
     aalborg
    -0.07
     MessageBoxButtons
    -0.07
    UNUSED
    -0.07
    POSITIVE LOGITS
     preference
    0.15
     prefer
    0.14
     Preference
    0.12
     prefers
    0.11
     preferences
    0.11
    Preference
    0.11
     Prefer
    0.10
     better
    0.09
     пÑĢедпоÑĩ
    0.09
     preferred
    0.09
    Activations Density 0.087%

    No Known Activations