INDEX

Explanations

the word "the" and phrases emphasizing values or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

¶Į

-0.18

áº¯t

-0.14

ç§

-0.14

anzi

-0.14

agues

-0.14

ë²Ī

-0.13

icus

-0.13

ãģıãĤĮãĤĭ

-0.13

nost

-0.13

ES

-0.13

POSITIVE LOGITS

 importance

0.54

 Importance

0.42

 value

0.38

 extent

0.38

 significance

0.36

extent

0.29

 impact

0.29

 role

0.28

 difference

0.27

 IMPORT

0.27

Activations Density 0.173%

the word "the" and phrases emphasizing values or significance

No Comments

No Known Activations