INDEX

Explanations

references to large entities or organizations, particularly those with significant financial power

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÏĩÏī

-0.18

immers

-0.15

lies

-0.14

ANGLES

-0.14

Ã²ng

-0.14

istrovstvÃŃ

-0.14

.NaN

-0.13

Geh

-0.13

Ø±Ø§Ø¯

-0.13

 WithEvents

-0.13

POSITIVE LOGITS

ieur

0.16

duino

0.16

0.15

ature

0.15

 Ã¶lÃ§

0.14

aille

0.14

©

0.14

erture

0.14

Uri

0.13

iris

0.13

Activations Density 0.009%

references to large entities or organizations, particularly those with significant financial power

No Comments

No Known Activations