INDEX

Explanations

specific structural or functional elements within a detailed description

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

 elsewhere

-0.15

addir

-0.15

_notifier

-0.14

arel

-0.14

metis

-0.14

 ëĭ¤ìĸĳ

-0.14

_usec

-0.14

tring

-0.13

ÏĦÎ®

-0.13

qid

-0.13

POSITIVE LOGITS

 upper

0.38

 middle

0.37

 lower

0.35

 outer

0.34

upper

0.32

middle

0.31

outer

0.29

lower

0.29

 central

0.26

 rear

0.26

Activations Density 0.417%

specific structural or functional elements within a detailed description

No Comments

No Known Activations