© 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 EvalsExportsAPI 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. 82957
    Prev
    Next
    INDEX
    Explanations

    references to sacrificial practices and religious rituals

    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
    URI
    -0.08
    cco
    -0.06
    STA
    -0.06
    ipel
    -0.06
     Fits
    -0.06
    iper
    -0.06
    oq
    -0.05
    acro
    -0.05
     provid
    -0.05
    ÛĮتÛĮ
    -0.05
    POSITIVE LOGITS
     sacrific
    0.10
     sacrifice
    0.10
     sacrifices
    0.09
     offerings
    0.09
     offering
    0.08
     tế
    0.08
     aday
    0.08
     sacrificing
    0.07
     sacrificed
    0.07
     sacr
    0.07
    Activations Density 0.079%

    No Known Activations