INDEX

Explanations

terms related to translation and bilingual communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ding

-0.19

icity

-0.17

hole

-0.17

des

-0.15

raig

-0.15

illa

-0.15

ÑģÐ»Ð¾Ð²

-0.15

dek

-0.15

ity

-0.15

POSITIVE LOGITS

/trans

0.24

 into

0.21

 Into

0.21

Into

0.21

AutoresizingMaskIntoConstraints

0.20

è¿ĩæĿ¥

0.18

oria

0.18

into

0.18

/local

0.17

 INTO

0.17

Activations Density 0.025%

terms related to translation and bilingual communication

No Comments

No Known Activations