INDEX

Explanations

equality and assignment statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

orman

-0.16

arde

-0.15

ZN

-0.14

ogn

-0.14

Ã©sz

-0.14

roker

-0.14

 Jacobs

-0.14

grave

-0.14

baugh

-0.14

aying

-0.14

POSITIVE LOGITS

ÐĶÐļ

0.16

alm

0.15

 Stateless

0.14

Ã¤l

0.14

Ø§Ø¦Ùħ

0.13

ãĥ³ãĥĲ

0.13

Ø§ÙĨØª

0.13

xdc

0.13

ToOne

0.13

ãĥ³ãĥĢ

0.13

Activations Density 0.067%

equality and assignment statements in code

No Comments

No Known Activations