INDEX

Explanations

phrases related to achievements and recognitions such as awards and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

achs

-0.15

usercontent

-0.14

íıĲ

-0.14

#End

-0.14

inoa

-0.14

etto

-0.13

 unas

-0.13

itus

-0.13

VERS

-0.13

Ð¾Ð·Ð½Ð°

-0.13

POSITIVE LOGITS

 TripAdvisor

0.16

 consecutive

0.16

uther

0.15

 recognition

0.15

 coveted

0.15

_cookies

0.15

è¿ŀ

0.14

ia

0.14

 prestigious

0.14

uyo

0.14

Activations Density 0.060%

phrases related to achievements and recognitions such as awards and citations

No Comments

No Known Activations