INDEX

Explanations

mathematical and scientific expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð½ÑĸÑģÑĤ

-0.16

ussy

-0.15

tera

-0.15

ndern

-0.14

eza

-0.13

owie

-0.13

.datab

-0.13

_DISABLED

-0.13

ãĥ©ãĥĥãĤ¯

-0.13

ØŃØ©

-0.13

POSITIVE LOGITS

ÌĤ

0.21

^(

0.21

á

0.21

âĤĢ

0.19

Hat

0.18

_hat

0.18

hat

0.18

 prime

0.18

ij

0.17

hat

0.17

Activations Density 0.140%

mathematical and scientific expressions

No Comments

No Known Activations