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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119094
    Prev
    Next
    INDEX
    Explanations

    references to deities and worship practices

    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
     ham
    -0.06
    sz
    -0.06
    èİ
    -0.06
    lor
    -0.06
    leta
    -0.06
     ing
    -0.06
     Kum
    -0.06
    Unc
    -0.05
     Lion
    -0.05
    éŨ
    -0.05
    POSITIVE LOGITS
     composite
    0.07
     Composite
    0.07
     خد
    0.07
     Gors
    0.07
    composite
    0.07
    '&&
    0.06
    arges
    0.06
     milfs
    0.06
    æĥij
    0.06
    Boom
    0.06
    Activations Density 0.002%

    No Known Activations