INDEX

Explanations

elements of conflict in discussions or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

WITHOUT

-0.19

 WITHOUT

-0.19

andon

-0.16

along

-0.15

enga

-0.15

aload

-0.15

íķĺëĬĶëį°

-0.15

ãĤ¥

-0.14

Ã³st

-0.14

WF

-0.14

POSITIVE LOGITS

nor

1.29

nor

1.02

Nor

0.99

Nor

0.90

NOR

0.74

 neither

0.63

 anymore

0.61

 sondern

0.52

 Ø¨ÙĦÚ©Ùĩ

0.46

 Neither

0.45

Activations Density 0.465%

elements of conflict in discussions or descriptions

No Comments

No Known Activations