INDEX

Explanations

phrases indicative of news and updates about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.scalablytyped

-0.15

ÐºÐ°Ð¿

-0.15

 preorder

-0.14

tic

-0.14

	snprintf

-0.14

nodoc

-0.14

.jasper

-0.14

AllowAnonymous

-0.14

zdy

-0.14

Rog

-0.13

POSITIVE LOGITS

 include

0.19

 nest

0.17

res

0.16

 Include

0.15

include

0.15

ensch

0.15

incy

0.15

 proven

0.14

 themes

0.14

Activations Density 0.344%

phrases indicative of news and updates about various topics

No Comments

No Known Activations