INDEX

Explanations

preprocessor directives and macros in programming code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ihan

-0.16

Ã©ru

-0.15

uelle

-0.15

.cn

-0.15

ervised

-0.14

age

-0.14

tre

-0.14

 tablesp

-0.14

enance

-0.14

hled

-0.14

POSITIVE LOGITS

gmt

0.18

__

0.17

Ð¾Ð½Ð¾Ð²

0.14

zure

0.14

Abs

0.14

hone

0.14

 amat

0.13

 ____

0.13

wel

0.13

Activations Density 0.020%

preprocessor directives and macros in programming code

No Comments

No Known Activations