INDEX

Explanations

"How" questions and inquiries about instructions or explanations

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

ksen

-0.15

uÅŁ

-0.15

jev

-0.15

Ã¶rt

-0.14

usk

-0.13

ianne

-0.13

Ã¢ng

-0.13

hci

-0.13

swick

-0.13

ÙĤØ¨

-0.13

POSITIVE LOGITS

‘

0.17

to

0.16

 your

0.16

>Main

0.14

kam

0.14

 recess

0.14

Ä±lacak

0.14

 Your

0.14

rah

0.14

lys

0.14

Activations Density 0.060%

"How" questions and inquiries about instructions or explanations

No Comments

No Known Activations