INDEX

Explanations

questions and phrases related to seeking assistance or gathering information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ayar

-0.15

.ht

-0.15

STRUCTOR

-0.14

hea

-0.14

(?

-0.14

(?)

-0.14

stras

-0.14

cheid

-0.13

 ?????

-0.13

tatus

-0.13

POSITIVE LOGITS

0.42

?↵

0.28

?"↵

0.24

ØŁ

0.24

ï¼Ł

0.23

?<

0.23

?↵↵

0.22

?).

0.22

?)↵

0.22

?č↵

0.21

Activations Density 0.099%

questions and phrases related to seeking assistance or gathering information

No Comments

No Known Activations