INDEX

Explanations

words related to limitations or constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

isÃ©

-0.16

asm

-0.16

ASM

-0.15

eza

-0.15

/***/

-0.14

ãĥ¼ãĥĦ

-0.14

izarre

-0.14

 Ð¿Ð¸ÑĤÐ°Ð½Ð¸Ñı

-0.14

INCLUDE

-0.14

asm

-0.14

POSITIVE LOGITS

ably

0.23

able

0.22

ables

0.18

yet

0.17

ingly

0.17

yet

0.17

 anywhere

0.17

edly

0.17

ulp

0.15

Yet

0.15

Activations Density 0.053%

words related to limitations or constraints

No Comments

No Known Activations