© 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. 38500
    Prev
    Next
    INDEX
    Explanations

    phrases that denote powers, rights, or permissions granted by authority

    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
    Ļæ±Ł
    -0.06
    linear
    -0.06
    ÑĤÑĢо
    -0.06
    gere
    -0.06
    zione
    -0.06
    ation
    -0.06
    eros
    -0.06
    up
    -0.06
    zero
    -0.06
    173
    -0.05
    POSITIVE LOGITS
     them
    0.09
     us
    0.08
    lava
    0.07
     him
    0.07
    ady
    0.07
    quences
    0.07
    alink
    0.07
     تÙĪسط
    0.07
     bợi
    0.07
    足
    0.06
    Activations Density 0.023%

    No Known Activations