INDEX

Explanations

coding concepts related to function definitions and parameter handling in programming

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fileprivate

-0.13

.Generated

-0.12

 cached

-0.12

 Disabled

-0.12

 dormant

-0.11

 caches

-0.11

\Active

-0.11

 deactivated

-0.11

ÑĥÐ·

-0.11

 IllegalStateException

-0.11

POSITIVE LOGITS

 argument

0.62

 arguments

0.60

 parameter

0.52

argument

0.51

 parameters

0.49

 Argument

0.49

arg

0.49

 Arguments

0.48

 param

0.47

arguments

0.47

Activations Density 0.118%

coding concepts related to function definitions and parameter handling in programming

No Comments

No Known Activations