INDEX

Explanations

elements related to disagreement or conflict in discussions

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

imon

-0.17

ummies

-0.15

division

-0.15

 Nath

-0.14

ChangeListener

-0.14

allon

-0.14

 grown

-0.14

anie

-0.14

antine

-0.14

issance

-0.14

POSITIVE LOGITS

inize

0.18

ibrate

0.18

ablish

0.18

ifies

0.17

apult

0.17

locate

0.17

ÏĦÎ±Î¹

0.16

lessly

0.16

å¥½äºĨ

0.16

uspend

0.15

Activations Density 0.118%

elements related to disagreement or conflict in discussions

No Comments

No Known Activations