INDEX

Explanations

instances of the word "in" and "the."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ceph

-0.16

IRD

-0.13

 customize

-0.13

zo

-0.13

ç¢

-0.13

phia

-0.13

ijken

-0.13

ìĸ´ê°Ģ

-0.13

ãĥ¼ãĤ¸

-0.13

rh

-0.13

POSITIVE LOGITS

ynet

0.17

nee

0.16

agu

0.16

oldt

0.15

.rpm

0.15

teÅŁ

0.14

zbo

0.14

ropic

0.14

egral

0.14

ë°°

0.14

Activations Density 0.048%

instances of the word "in" and "the."

No Comments

No Known Activations