INDEX

Explanations

numerical values related to statistics or measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÑĥÑĢÑĥ

-0.17

isser

-0.15

 pushViewController

-0.14

Äı

-0.14

 ÙĪØ´

-0.14

izik

-0.14

ãĥ³ãĥĪ

-0.14

Ħ

-0.14

.liferay

-0.14

vae

-0.13

POSITIVE LOGITS

pq

0.15

ually

0.14

ply

0.14

 malt

0.14

etten

0.14

 conf

0.14

mot

0.14

reur

0.13

este

0.13

wet

0.13

Activations Density 0.011%

numerical values related to statistics or measurement

No Comments

No Known Activations