INDEX

Explanations

numerical values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

YNC

-0.17

esch

-0.16

 yearly

-0.16

 annual

-0.16

 Rudd

-0.16

essler

-0.15

 sadd

-0.15

anja

-0.14

ersions

-0.14

eger

-0.14

POSITIVE LOGITS

/per

0.21

ìĶ©

0.15

 chÃ³ng

0.15

gnore

0.15

(Keys

0.15

ä¹ĭ

0.14

 Choi

0.14

 ÙħØ±Ø¨Ø¹

0.14

rette

0.14

 TERMS

0.14

Activations Density 0.082%

numerical values and measurements

No Comments

No Known Activations