INDEX

Explanations

non-English characters or special symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

zin

-0.16

erif

-0.16

dux

-0.16

odable

-0.15

ChangeEvent

-0.15

adÄ±r

-0.14

hydr

-0.14

uida

-0.14

izik

-0.14

èĪª

-0.13

POSITIVE LOGITS

 twice

0.19

 Twice

0.19

 bull

0.18

 Echo

0.17

 keer

0.17

bull

0.16

cup

0.16

ÑĢÐ°Ð²Ð¸

0.15

Ron

0.15

 Play

0.15

Activations Density 0.022%

non-English characters or special symbols

No Comments

No Known Activations