INDEX

Explanations

URLs and links in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ahren

-0.17

ysz

-0.15

 addCriterion

-0.15

ÄĽn

-0.15

ollow

-0.15

rie

-0.14

Ãły

-0.14

.shiro

-0.14

ENTA

-0.14

IGHT

-0.14

POSITIVE LOGITS

ÑģÐ¾Ð½

0.15

ips

0.15

 cons

0.15

0.14

 equal

0.14

 Purch

0.14

erse

0.14

Tay

0.14

ezi

0.14

 Classic

0.13

Activations Density 0.015%

URLs and links in the text

No Comments

No Known Activations