INDEX

Explanations

terms related to cryptographic keys and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iske

-0.18

wil

-0.16

iev

-0.14

íĥĪ

-0.14

oose

-0.14

acter

-0.14

 Sche

-0.14

 è»Ĭ

-0.14

hv

-0.14

oje

-0.13

POSITIVE LOGITS

/MPL

0.16

.twig

0.14

ercial

0.14

charg

0.14

kte

0.13

ERO

0.13

mlink

0.13

etty

0.13

ÑĬÐµÐ¼

0.13

etti

0.13

Activations Density 0.011%

terms related to cryptographic keys and addresses

No Comments

No Known Activations