INDEX

Explanations

references to military presence and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Johns

-0.15

 ØªÙĦ

-0.14

 Owens

-0.14

 æ©

-0.14

Ð¾Ð»Ð¸ÑĤ

-0.14

fÃ¼

-0.14

abbit

-0.13

 Flem

-0.13

-buffer

-0.13

aza

-0.13

POSITIVE LOGITS

Tu

0.23

 Pants

0.20

Mi

0.20

Tu

0.20

Tup

0.19

Su

0.17

Mi

0.17

 Cosmos

0.16

Suk

0.16

ãĤĤãģ£ãģ¨

0.16

Activations Density 0.021%

references to military presence and operations

No Comments

No Known Activations