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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120305
    Prev
    Next
    INDEX
    Explanations

    references to superstition and its implications in society

    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
    aisy
    -0.07
     вд
    -0.07
    irez
    -0.07
    à¹Ģà¸Ļ
    -0.06
    988
    -0.06
     forgiving
    -0.06
    felt
    -0.06
     دÙģ
    -0.06
    ÅĤug
    -0.06
    quan
    -0.06
    POSITIVE LOGITS
     science
    0.12
     Science
    0.11
    science
    0.10
    Science
    0.10
     scientific
    0.09
    ç§ijåѦ
    0.09
     superst
    0.08
     belief
    0.08
     Scientific
    0.08
     sciences
    0.07
    Activations Density 0.030%

    No Known Activations