INDEX

Explanations

instances of the word "that" and variations of its context within the text

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

ãģĤãĤĬ

-0.20

Ùĩ

-0.19

ãģĤãĤĭ

-0.19

ãģĤãģ£ãģŁ

-0.18

amp

-0.18

-0.17

us

-0.15

sans

-0.15

ised

-0.14

esktop

-0.14

POSITIVE LOGITS

 particular

0.37

ched

0.35

 same

0.31

/th

0.31

zelf

0.28

-ÑĤÐ¾

0.26

 PARTICULAR

0.25

 SAME

0.23

 Ð¶Ðµ

0.23

ching

0.23

Activations Density 0.195%

instances of the word "that" and variations of its context within the text

No Comments

No Known Activations