INDEX

Explanations

configuration settings related to software components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

elpers

-0.17

steder

-0.16

>>

-0.16

arge

-0.15

 >>↵↵

-0.15

flen

-0.15

 Parker

-0.15

.gg

-0.14

POSITIVE LOGITS

xsi

0.22

/>↵

0.19

 />↵

0.19

 xlink

0.17

 /></

0.17

 DisplayName

0.16

><![

0.15

%)↵

0.15

 rendition

0.15

/>č↵

0.15

Activations Density 0.156%

configuration settings related to software components

No Comments

No Known Activations