INDEX

Explanations

phrases that indicate repetition and established methods

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

pp

-0.16

meer

-0.15

 stance

-0.14

.innerHeight

-0.14

stance

-0.14

.YELLOW

-0.14

erte

-0.13

encies

-0.13

itus

-0.13

iming

-0.13

POSITIVE LOGITS

 trib

0.26

è©¦

0.24

 trial

0.23

è¯ķ

0.22

 Trib

0.21

 tried

0.21

try

0.20

trial

0.20

 Trial

0.20

Trial

0.19

Activations Density 0.018%

phrases that indicate repetition and established methods

No Comments

No Known Activations