© 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. 38453
    Prev
    Next
    INDEX
    Explanations

    references to policy measures and their effectiveness regarding public health and safety

    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
    bidden
    -0.06
    processable
    -0.06
    ULLET
    -0.06
    loquent
    -0.06
    orney
    -0.06
    928
    -0.06
    åħģ
    -0.06
    imler
    -0.06
     normal
    -0.05
    592
    -0.05
    POSITIVE LOGITS
     effectiveness
    0.15
     efficacy
    0.11
     ineffective
    0.11
     effective
    0.10
     Effective
    0.10
    æķĪæŀľ
    0.09
    -effective
    0.09
     íļ¨ê³¼
    0.09
    Effective
    0.08
     targeting
    0.08
    Activations Density 0.049%

    No Known Activations