© 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. 30-LLAMASCOPE-RES-32K
    11. 23905
    Prev
    Next
    INDEX
    Explanations

    instances of exception handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ErrorMessage
    -0.19
    WithError
    -0.18
    /error
    -0.17
    /Error
    -0.17
     erro
    -0.17
    ClassLoader
    -0.17
    errorMessage
    -0.17
    erro
    -0.16
     isError
    -0.16
    .setError
    -0.16
    POSITIVE LOGITS
    _runtime
    0.21
     runtime
    0.21
    _logic
    0.20
    insi
    0.19
     illegal
    0.19
    Logic
    0.18
    -runtime
    0.18
     Logic
    0.18
    runtime
    0.18
     Impro
    0.18
    Activations Density 0.044%

    No Known Activations