INDEX

Explanations

the word "so" and its variations, indicating a focus on expressions of consequence or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ay

-0.16

uel

-0.16

oki

-0.15

ouse

-0.15

ur

-0.14

ello

-0.14

ousse

-0.14

upa

-0.14

reh

-0.14

_DO

-0.14

POSITIVE LOGITS

are

0.45

 were

0.35

_are

0.30

 Ð±ÑĥÐ´ÑĥÑĤ

0.27

 ÑıÐ²Ð»ÑıÑİÑĤÑģÑı

0.26

 ÙĩØ³ØªÙĨØ¯

0.26

ARE

0.25

 sÄħ

0.24

.are

0.24

Are

0.23

Activations Density 0.053%

the word "so" and its variations, indicating a focus on expressions of consequence or emphasis

No Comments

No Known Activations