INDEX

Explanations

phrases related to significant achievements or performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Malik

-0.15

¬ģ

-0.15

...]↵↵

-0.15

_CT

-0.15

lectual

-0.15

.LENGTH

-0.15

 kÃ¸

-0.15

 Heard

-0.15

heets

-0.14

åİ

-0.14

POSITIVE LOGITS

Moh

0.16

steen

0.14

iesen

0.14

 rouge

0.14

0.13

 tele

0.13

TEL

0.13

steel

0.13

sted

0.13

Activations Density 0.071%

phrases related to significant achievements or performances

No Comments

No Known Activations