INDEX

Explanations

references to significant historical events or figures and their influence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Obama

-0.19

Û²Û°Û±

-0.18

 recent

-0.18

iferay

-0.17

ä»Ĭå¹´

-0.17

Dro

-0.16

 latest

-0.16

 recently

-0.15

 Recent

-0.15

POSITIVE LOGITS

0.49

0.41

0.32

Û±Û¹Û¸

0.29

 Reagan

0.25

Û±Û¹Û¹

0.24

 USSR

0.23

 AIDS

0.22

 Thatcher

0.22

 Soviet

0.22

Activations Density 0.994%

references to significant historical events or figures and their influence

No Comments

No Known Activations