INDEX

Explanations

specific names and titles associated with personal achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.wr

-0.16

ocop

-0.16

Ã¡la

-0.15

liÄį

-0.15

uct

-0.15

ulous

-0.14

tae

-0.14

sent

-0.14

aret

-0.14

aaa

-0.14

POSITIVE LOGITS

.biz

0.15

oran

0.15

ythe

0.14

Ð´Ð¸Ð½Ð°

0.14

transparent

0.14

 à¤²à¤Ĺà¤¤

0.14

 transparent

0.13

tuÄŁ

0.13

RAD

0.13

RequestId

0.13

Activations Density 0.323%

specific names and titles associated with personal achievements

No Comments

No Known Activations