INDEX

Explanations

references to major entities or categories, particularly in advertising and product classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

enson

-0.16

ych

-0.15

irst

-0.14

ãĥĭãĤ¢

-0.14

inator

-0.14

ISCO

-0.14

aving

-0.13

ypi

-0.13

kj

-0.13

POSITIVE LOGITS

/min

0.19

accept

0.18

-league

0.17

stery

0.17

eum

0.17

erus

0.17

ceed

0.16

aris

0.16

aukee

0.15

ãĥ£

0.15

Activations Density 0.035%

references to major entities or categories, particularly in advertising and product classifications

No Comments

No Known Activations