INDEX

Explanations

phrases indicating formal investigations or inquiries into various incidents or issues

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

 flames

-0.15

olec

-0.15

inen

-0.14

anan

-0.14

Ð¾Ð´ÐµÑĢÐ¶

-0.14

-0.13

regon

-0.13

acket

-0.13

ADI

-0.13

mith

-0.13

POSITIVE LOGITS

 whether

0.24

æĺ¯åĲ¦

0.20

 Whether

0.18

whether

0.17

 æĺ¯åĲ¦

0.16

aris

0.16

 WHETHER

0.16

åĪ°åºķ

0.16

 possible

0.15

Whether

0.15

Activations Density 0.063%

phrases indicating formal investigations or inquiries into various incidents or issues

No Comments

No Known Activations