INDEX

Explanations

the word "the" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Bottom

-0.14

hol

-0.14

 Zucker

-0.14

pn

-0.14

mid

-0.14

 okul

-0.14

Sle

-0.14

rite

-0.14

 Columbia

-0.14

POSITIVE LOGITS

 extent

0.17

extent

0.15

ilver

0.15

 Hyde

0.15

.RunWith

0.15

Ø¹Ø¯Ø¯

0.15

ellido

0.14

 achter

0.14

ëª©

0.14

elen

0.14

Activations Density 0.014%

the word "the" in various contexts

No Comments

No Known Activations