INDEX

Explanations

diplomatic and international relations terms

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

 Ð¿ÑĢÐ°Ð²Ð°

-0.15

uem

-0.15

isci

-0.14

æĿĥ

-0.14

borg

-0.14

 rebell

-0.14

.gstatic

-0.14

-0.13

OUSE

-0.13

POSITIVE LOGITS

 bilateral

0.36

Bil

0.33

bil

0.32

bil

0.30

 mutually

0.25

 mutual

0.24

 exchanged

0.23

 exchanges

0.20

 Mutual

0.19

 reciprocal

0.19

Activations Density 0.135%

diplomatic and international relations terms

No Comments

No Known Activations