INDEX

Explanations

references to the LG brand and its products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ermal

-0.18

ho

-0.17

igua

-0.16

anga

-0.15

igh

-0.15

Ð¾Ð¶ÐµÑĤ

-0.14

igger

-0.14

icense

-0.14

.userInteractionEnabled

-0.14

ulong

-0.13

POSITIVE LOGITS

LG

0.28

 Thin

0.22

LG

0.21

 Optim

0.19

Thin

0.19

/lg

0.19

lg

0.18

AI

0.17

Urb

0.17

 MÃ¶

0.17

Activations Density 0.011%

references to the LG brand and its products

No Comments

No Known Activations