INDEX

Explanations

affirmative and supportive expressions related to personal experiences and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Another

-0.19

Another

-0.18

 another

-0.18

åı¦å¤ĸ

-0.17

nation

-0.17

another

-0.16

 Cassidy

-0.16

 additionally

-0.16

asers

-0.15

aps

-0.15

POSITIVE LOGITS

 respectively

0.19

 *----------------------------------------------------------------

0.16

 topl

0.16

Ø±Ø§Ø¯

0.15

 à¹Ĩ

0.15

.GetAsync

0.15

hone

0.14

iVar

0.14

 filmer

0.14

.CreateCommand

0.14

Activations Density 0.067%

affirmative and supportive expressions related to personal experiences and relationships

No Comments

No Known Activations