INDEX

Explanations

specific terms and phrases related to digital security and technical jargon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iten

-0.16

anlÄ±

-0.15

inka

-0.14

_HEADERS

-0.14

 nostr

-0.14

arel

-0.14

inis

-0.14

imson

-0.14

isini

-0.14

ig

-0.13

POSITIVE LOGITS

 both

0.22

both

0.21

Both

0.20

_both

0.20

 Both

0.19

 neither

0.18

epar

0.17

 BOTH

0.16

ernes

0.15

Å¡k

0.15

Activations Density 0.197%

specific terms and phrases related to digital security and technical jargon

No Comments

No Known Activations