INDEX

Explanations

phrases related to governmental and authority entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

phins

-0.16

èĪĮ

-0.14

abay

-0.14

 overrun

-0.14

ventory

-0.14

 Forgot

-0.14

éģ£

-0.14

è¡Ŀ

-0.13

atorium

-0.13

Ĥæķ°

-0.13

POSITIVE LOGITS

Bounding

0.15

trl

0.15

ÑĥÑĩ

0.14

 mainstream

0.13

wh

0.13

substr

0.13

 wide

0.13

Bru

0.13

ourn

0.13

Activations Density 0.138%

phrases related to governmental and authority entities

No Comments

No Known Activations