INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

fel

-0.15

ilir

-0.15

sel

-0.14

fef

-0.14

fel

-0.14

ILLA

-0.14

erra

-0.14

ÐµÑģÐ°

-0.13

illa

-0.13

quette

-0.13

POSITIVE LOGITS

 support

0.27

æĶ¯æĮģ

0.21

 Support

0.21

/support

0.20

_support

0.20

Support

0.20

 Ð¿Ð¾Ð´Ð´ÐµÑĢÐ¶

0.19

upport

0.19

support

0.19

 supportive

0.19

Activations Density 0.068%

expressions of gratitude and appreciation

No Comments

No Known Activations