INDEX

Explanations

concepts related to simplicity and ease of understanding, particularly in complex situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

à¤Ĺà¤°

-0.14

aravel

-0.14

asso

-0.14

à¹Ģà¸¥à¸¢

-0.14

att

-0.13

éļĨ

-0.13

Reserved

-0.13

ATUS

-0.13

catid

-0.13

 Bowman

-0.13

POSITIVE LOGITS

 easily

0.44

able

0.43

 Easily

0.42

 easy

0.40

æĺĵ

0.37

 easier

0.35

 ÙĤØ§Ø¨ÙĦ

0.35

izable

0.35

 readily

0.35

åı¯

0.35

Activations Density 0.298%

concepts related to simplicity and ease of understanding, particularly in complex situations

No Comments

No Known Activations