INDEX

Explanations

instances of the word "Invalid" along with other mentions of invalid data or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

inho

-0.17

orro

-0.16

acher

-0.15

wort

-0.15

.cn

-0.15

itzer

-0.15

.nz

-0.14

iras

-0.14

æķ·

-0.14

imson

-0.14

POSITIVE LOGITS

ÑģÑĤÐ°

0.15

usher

0.14

mentor

0.14

amba

0.13

eer

0.13

enci

0.13

ated

0.13

Ð½Ð°Ð²

0.13

Activations Density 0.008%

instances of the word "Invalid" along with other mentions of invalid data or conditions

No Comments

No Known Activations