INDEX

Explanations

terms related to superiority, quality, and significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

imento

-0.19

lenÃŃ

-0.17

ement

-0.16

ÙĨÙī

-0.15

eros

-0.15

ationship

-0.15

Ã¼rn

-0.15

atos

-0.14

uda

-0.14

aggio

-0.14

POSITIVE LOGITS

itchen

0.16

°

0.14

æ··

0.14

icontrol

0.14

line

0.14

corp

0.13

cott

0.13

bery

0.13

 Greenland

0.13

enk

0.13

Activations Density 0.063%

terms related to superiority, quality, and significance in various contexts

No Comments

No Known Activations