INDEX

Explanations

phrases referencing significant ideas or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

idable

-0.14

ovic

-0.13

 contrasts

-0.13

ç¥¥

-0.13

iders

-0.13

olt

-0.13

rada

-0.13

burg

-0.12

adero

-0.12

POSITIVE LOGITS

 thing

0.43

 reason

0.39

 problem

0.33

 interesting

0.33

 Thing

0.30

 beauty

0.30

 funny

0.30

Thing

0.29

thing

0.29

key

0.28

Activations Density 0.293%

phrases referencing significant ideas or concepts

No Comments

No Known Activations