INDEX

Explanations

phrases related to challenges or obstacles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ador

-0.16

igar

-0.16

edom

-0.16

exion

-0.16

egin

-0.15

 magna

-0.15

itar

-0.14

lfw

-0.14

aten

-0.14

idal

-0.13

POSITIVE LOGITS

 second

0.35

 Secondly

0.35

second

0.29

ç¬¬äºĮ

0.27

 ç¬¬äºĮ

0.26

-second

0.24

(second

0.23

 SECOND

0.23

 another

0.23

.second

0.23

Activations Density 0.057%

phrases related to challenges or obstacles

No Comments

No Known Activations