INDEX

Explanations

the opening parentheses in the text

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

jvu

-0.17

.appspot

-0.15

ughters

-0.14

erve

-0.13

enus

-0.13

utorials

-0.13

lfw

-0.13

criptors

-0.13

ersist

-0.13

amas

-0.13

POSITIVE LOGITS

Zuk

0.15

orch

0.15

arak

0.13

 Levy

0.13

CHIP

0.13

rome

0.12

 pragma

0.12

 stripslashes

0.12

iÃ©n

0.12

 ÐºÐ¾Ð²

0.12

Activations Density 0.524%

the opening parentheses in the text

No Comments

No Known Activations