INDEX

Explanations

terms related to software components, policies, and security issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

HeaderCode

-0.16

FAULT

-0.16

ream

-0.15

uhl

-0.14

toc

-0.14

Cay

-0.14

ToProps

-0.14

isers

-0.13

indre

-0.13

 Wenger

-0.13

POSITIVE LOGITS

Chrome

0.23

 Chrome

0.23

 chrome

0.22

RefPtr

0.20

.Chrome

0.20

chrome

0.20

ç«

0.19

idl

0.19

mojom

0.19

WebKit

0.18

Activations Density 0.030%

terms related to software components, policies, and security issues

No Comments

No Known Activations