INDEX

Explanations

references to academic programs and initiatives

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

ITA

-0.14

\Active

-0.14

imilar

-0.13

call

-0.13

 Carousel

-0.13

Ð¾ÑĢÑĭ

-0.13

<->

-0.13

 TypeName

-0.13

Carrier

-0.13

 wrong

-0.13

POSITIVE LOGITS

igne

0.15

Fat

0.15

LOS

0.14

elage

0.14

Ä

0.14

dana

0.14

-fat

0.14

inals

0.13

NavController

0.13

 eles

0.13

Activations Density 0.046%

references to academic programs and initiatives

No Comments

No Known Activations