© 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. 31-LLAMASCOPE-RES-32K
    11. 10500
    Prev
    Next
    INDEX
    Explanations

    terms related to gambling, investments, and financial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utilise
    -0.19
     requisite
    -0.18
     permitting
    -0.18
     utilized
    -0.17
    Centre
    -0.17
    permit
    -0.17
     amongst
    -0.17
     permits
    -0.17
     commenced
    -0.16
     attained
    -0.16
    POSITIVE LOGITS
    0.28
     They
    0.22
     It
    0.21
    Ì
    0.20
     There
    0.17
     You
    0.17
    They
    0.16
     This
    0.16
    It
    0.15
     To
    0.15
    Activations Density 0.179%

    No Known Activations