INDEX

Explanations

words and phrases related to exploration and discovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

imals

-0.17

aphore

-0.17

statt

-0.17

ARA

-0.16

uate

-0.15

arkan

-0.15

uracy

-0.15

emain

-0.15

iker

-0.15

kola

-0.15

POSITIVE LOGITS

 minded

0.17

 depths

0.16

-minded

0.16

 Depths

0.15

andex

0.14

leyen

0.14

(TEXT

0.14

DateFormat

0.14

 Sunrise

0.13

 Ø¯ÙĤÛĮÙĤ

0.13

Activations Density 0.027%

words and phrases related to exploration and discovery

No Comments

No Known Activations