INDEX

Explanations

references to specific locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

¥

-0.15

ÑģÐ»

-0.14

.eq

-0.14

erman

-0.14

 solid

-0.14

QL

-0.14

 Banks

-0.14

 Magn

-0.14

 Gross

-0.14

<path

-0.13

POSITIVE LOGITS

åĬĽçļĦ

0.18

ÐłÐĿ

0.16

ÐµÑģÐ°

0.16

SSIP

0.15

åĬĽ

0.15

 Visibility

0.15

Ð³ÑĢÐ°

0.15

 Shorts

0.14

 Intersection

0.14

 nisi

0.14

Activations Density 0.023%

references to specific locations or places

No Comments

No Known Activations