INDEX

Explanations

elements of programming code or syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

enge

-0.15

oke

-0.14

ÎµÎ²

-0.14

anoi

-0.14

ati

-0.14

-0.13

.TestTools

-0.13

 Continued

-0.13

elf

-0.13

wat

-0.13

POSITIVE LOGITS

 return

0.98

return

0.86

	return

0.72

-return

0.71

 Return

0.68

 returning

0.64

Return

0.63

.return

0.60

 returns

0.59

 RETURN

0.59

Activations Density 0.148%

elements of programming code or syntax

No Comments

No Known Activations