INDEX

Explanations

negative punctuation or symbols indicating strong disapproval

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ungan

-0.16

rish

-0.15

 Mali

-0.15

.Metro

-0.14

XObject

-0.14

 crossorigin

-0.14

noc

-0.14

.jet

-0.14

;br

-0.14

ousel

-0.13

POSITIVE LOGITS

 Watches

0.27

 watches

0.26

 watch

0.23

-watch

0.22

Hy

0.21

 wearer

0.21

watch

0.20

_watch

0.20

 Basel

0.20

Hy

0.20

Activations Density 0.000%

negative punctuation or symbols indicating strong disapproval

No Comments

No Known Activations