INDEX

Explanations

proper nouns, specifically names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Fle

-0.16

ä¸Ī

-0.15

ØµØ¯

-0.14

Ð¾Ð¿Ð¸Ñģ

-0.14

ãĥĨãĥ«

-0.14

akes

-0.14

ake

-0.13

 Flush

-0.13

tel

-0.13

epar

-0.13

POSITIVE LOGITS

baugh

0.15

gnore

0.15

burg

0.15

indre

0.14

 ÙĨÙģØ³Ùĩ

0.14

 supra

0.13

ãģŁãģ¡ãģ®

0.13

ĶåĽŀ

0.13

OURS

0.13

Activations Density 0.040%

proper nouns, specifically names of people

No Comments

No Known Activations