© 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. 89576
    Prev
    Next
    INDEX
    Explanations

    multiple references to the number 170, indicating a strong focus on standards or specifications denoted by this number

    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
    baugh
    -0.07
    strand
    -0.07
    elves
    -0.07
    екÑĤи
    -0.07
    anter
    -0.07
    atron
    -0.07
    pter
    -0.06
    oref
    -0.06
    ably
    -0.06
    akers
    -0.06
    POSITIVE LOGITS
    aging
    0.07
     Inbox
    0.06
    createForm
    0.06
    ente
    0.06
    áž
    0.06
    qid
    0.06
    زÙĩ
    0.06
    BT
    0.05
     demon
    0.05
    ennis
    0.05
    Activations Density 0.005%

    No Known Activations