INDEX

Explanations

phrases emphasizing the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.22

Ùĩ

-0.20

ãģĤãģ£ãģŁ

-0.19

-0.18

ãģĤãĤĭ

-0.18

amp

-0.18

sans

-0.16

sic

-0.16

sie

-0.16

sdale

-0.15

POSITIVE LOGITS

ched

0.39

 particular

0.38

 same

0.34

/th

0.33

zelf

0.29

 PARTICULAR

0.27

ching

0.27

 SAME

0.25

 Ð¶Ðµ

0.25

-ÑĤÐ¾

0.24

Activations Density 0.205%

phrases emphasizing the word "that" in various contexts

No Comments

No Known Activations