INDEX

Explanations

similarities and comparisons expressed through the word "as."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

evice

-0.15

PTION

-0.15

iped

-0.14

ÑĢÐµÐ±

-0.14

erta

-0.14

CHANT

-0.14

.weixin

-0.14

 ØŃØªÛĮ

-0.13

Ø¨ÙĦ

-0.13

POSITIVE LOGITS

 though

0.47

if

0.44

though

0.34

 Though

0.33

Though

0.32

if

0.27

if

0.24

_if

0.24

 ÐµÑģÐ»Ð¸

0.23

 usual

0.23

Activations Density 0.106%

similarities and comparisons expressed through the word "as."

No Comments

No Known Activations