INDEX

Explanations

instances of the word "we" indicating a sense of collective experience or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

arÃŃa

-0.14

 à¤²à¤Ĺà¤¤

-0.14

osi

-0.14

ear

-0.14

mit

-0.13

ukan

-0.13

:CGRect

-0.13

uries

-0.13

lest

-0.13

oure

-0.13

POSITIVE LOGITS

 discussed

0.25

 both

0.24

 discussion

0.23

all

0.22

 discussing

0.21

 agreed

0.21

 discusses

0.21

 discuss

0.20

ird

0.20

both

0.20

Activations Density 0.280%

instances of the word "we" indicating a sense of collective experience or action

No Comments

No Known Activations