INDEX

Explanations

the word "out" 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

erties

-0.17

è¡

-0.15

Moy

-0.15

lig

-0.15

cker

-0.15

ination

-0.14

Ã©t

-0.14

variant

-0.14

ijing

-0.13

 Scalars

-0.13

POSITIVE LOGITS

 there

0.27

out

0.26

there

0.21

Out

0.20

 THERE

0.19

There

0.17

.out

0.17

wards

0.17

 dere

0.17

LOUD

0.17

Activations Density 0.014%

the word "out" in various contexts

No Comments

No Known Activations