INDEX

Explanations

conditional phrases or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

áº¢

-0.15

ä¼Ļ

-0.14

/reg

-0.14

 pure

-0.14

/tr

-0.13

rome

-0.13

DEX

-0.13

angelo

-0.13

 incons

-0.13

 supposed

-0.13

POSITIVE LOGITS

0.17

fy

0.16

uzzer

0.15

ufs

0.15

cales

0.14

ãĥ³ãĥĩãĤ£

0.14

rames

0.14

endi

0.14

borrow

0.14

iddle

0.14

Activations Density 0.010%

conditional phrases or statements

No Comments

No Known Activations