© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127643
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of withdrawing or retraction in various contexts

    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
    agra
    -0.07
    FU
    -0.07
    enna
    -0.06
    lesia
    -0.06
     TValue
    -0.06
    curring
    -0.06
     Kardash
    -0.06
    quette
    -0.06
    637
    -0.06
    uraa
    -0.06
    POSITIVE LOGITS
     withdrawn
    0.10
     withdrawal
    0.10
     withdraw
    0.10
     withdrawing
    0.09
     withdrew
    0.09
    withdraw
    0.08
     Withdraw
    0.08
    Withdraw
    0.08
     withdrawals
    0.07
     previously
    0.07
    Activations Density 0.015%

    No Known Activations