INDEX

Explanations

terms related to responsibilities and their implications, especially concerning companies and individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

raquo

-0.15

iola

-0.14

rost

-0.14

getattr

-0.13

-haspopup

-0.13

áºŃy

-0.13

ennes

-0.13

áº£o

-0.13

ëĸ

-0.12

essler

-0.12

POSITIVE LOGITS

 both

1.17

both

1.07

 BOTH

1.02

 Both

0.93

Both

0.91

 bÃ¥de

0.83

_both

0.79

 ambos

0.67

_BOTH

0.65

 beide

0.65

Activations Density 0.711%

terms related to responsibilities and their implications, especially concerning companies and individuals

No Comments

No Known Activations