INDEX

Explanations

terms related to education and institutional issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ï»¿using

-0.20

duit

-0.16

celik

-0.16

 ###↵

-0.16

/*č↵

-0.15

ceb

-0.15

eydi

-0.15

 mech

-0.14

inston

-0.14

porto

-0.14

POSITIVE LOGITS

 [âĢ¦

0.21

 [âĢ¦]

0.20

 Ã¢

0.19

‘

0.18

Ã¢

0.17

“

0.16

 âĢ¦

0.15

 ghost

0.15

âĢ¦

0.15

âĢĲ

0.15

Activations Density 0.123%

terms related to education and institutional issues

No Comments

No Known Activations