INDEX

Explanations

the conjunction "and" used 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ñŀ

-0.16

arus

-0.16

Ä©

-0.15

MMdd

-0.15

immers

-0.14

Äħ

-0.14

ãĤ¥

-0.14

repositories

-0.14

ovÃŃ

-0.13

onga

-0.13

POSITIVE LOGITS

 ourselves

0.24

0.22

 yourself

0.20

me

0.19

me

0.18

chwitz

0.17

 Yourself

0.17

èĩªå·±

0.17

ale

0.16

our

0.16

Activations Density 0.025%

the conjunction "and" used in various contexts

No Comments

No Known Activations