INDEX

Explanations

quotes or dialogue elements within the text

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

ispers

-0.19

kers

-0.17

afia

-0.15

Ð¾ÑĢÐ¾Ð¶

-0.15

rray

-0.15

IntPtr

-0.14

ÃºÄįast

-0.14

wl

-0.14

batis

-0.14

ISTER

-0.14

POSITIVE LOGITS

LICENSE

0.20

License

0.17

ed

0.17

lic

0.16

est

0.16

land

0.16

Dub

0.16

gio

0.15

_license

0.15

license

0.15

Activations Density 0.026%

quotes or dialogue elements within the text

No Comments

No Known Activations