INDEX

Explanations

mentions of grocery-related terms and stores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

quin

-0.16

maries

-0.15

Ð²Ð¾Ð´

-0.15

ab

-0.14

ï¸ı

-0.14

uin

-0.14

 marin

-0.14

wn

-0.14

undi

-0.13

POSITIVE LOGITS

avia

0.18

PRINTF

0.17

.sponge

0.17

uibModal

0.16

unca

0.16

/pub

0.15

ijn

0.15

ehler

0.15

ystate

0.15

ylie

0.14

Activations Density 0.018%

mentions of grocery-related terms and stores

No Comments

No Known Activations