INDEX

Explanations

events or actions related to negotiation or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iap

-0.15

utin

-0.13

 pÅĻitom

-0.13

à¤¾à¤¯à¤¤

-0.13

ëħĦìĹĲëĬĶ

-0.13

cko

-0.12

½æķ°

-0.12

 Across

-0.12

 eldre

-0.12

ëł¤

-0.11

POSITIVE LOGITS

 after

1.22

after

0.96

 Ð¿Ð¾ÑģÐ»Ðµ

0.86

 dopo

0.85

 After

0.84

After

0.81

 AFTER

0.81

_after

0.81

 aprÃ¨s

0.75

-after

0.75

Activations Density 1.408%

events or actions related to negotiation or conflict

No Comments

No Known Activations