INDEX

Explanations

terms related to review and feedback processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

zsche

-0.18

staking

-0.18

ÐµÑĢÐ°Ð¿

-0.17

osity

-0.17

strap

-0.15

kek

-0.15

.scalablytyped

-0.15

EMPLARY

-0.15

Äįer

-0.15

Ã¼lt

-0.14

POSITIVE LOGITS

0.19

ub

0.16

ver

0.15

enn

0.14

ogue

0.13

nce

0.13

ãĤ¦ãĥĪ

0.13

 proportion

0.13

Ĵ

0.13

Activations Density 0.300%

terms related to review and feedback processes

No Comments

No Known Activations