INDEX

Explanations

instances of the word "them."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 itself

-0.26

Ø§ÙĨÙĩ

-0.20

ibly

-0.19

ovna

-0.17

_DECREF

-0.16

quine

-0.15

(es

-0.15

taire

-0.15

odge

-0.15

bucks

-0.15

POSITIVE LOGITS

/us

0.48

/her

0.43

self

0.38

atically

0.35

/th

0.34

elves

0.32

zelf

0.28

SELF

0.26

 selves

0.25

SEL

0.24

Activations Density 0.156%

instances of the word "them."

No Comments

No Known Activations