© 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. 13-LLAMASCOPE-RES-32K
    11. 16429
    Prev
    Next
    INDEX
    Explanations

    references to Christianity and religious themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secular
    -0.19
    ephir
    -0.17
    rait
    -0.15
    aktu
    -0.15
     validationResult
    -0.15
    ibr
    -0.15
    urse
    -0.15
     atheist
    -0.14
     ÙģÙĨ
    -0.14
    оÑı
    -0.14
    POSITIVE LOGITS
     gloss
    0.15
     sup
    0.15
     Christ
    0.14
     ard
    0.14
    enza
    0.14
    locker
    0.14
     gray
    0.14
     Xt
    0.13
     Nic
    0.13
     Deliver
    0.13
    Activations Density 0.881%

    No Known Activations