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

    Neuronpedia

    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. 29-LLAMASCOPE-RES-32K
    11. 18364
    Prev
    Next
    INDEX
    Explanations

    patterns in gaming rules and regulations, including references to exceptions and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rated
    -0.15
     /*#__
    -0.15
     WARRANTY
    -0.15
     Reservation
    -0.15
    Reservation
    -0.15
    rez
    -0.15
    å¹ķ
    -0.14
    739
    -0.14
    139
    -0.14
     Registr
    -0.14
    POSITIVE LOGITS
     rule
    1.24
     rules
    1.16
     Rule
    1.08
    -rule
    1.04
    rule
    1.04
     Rules
    1.02
     RULE
    1.00
    Rule
    1.00
    rules
    0.98
    _rule
    0.96
    Activations Density 0.227%

    No Known Activations