INDEX

Explanations

references to the quantity or amount of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ike

-0.15

nga

-0.14

Ã½Å¡

-0.14

feld

-0.14

,LOCATION

-0.14

 Same

-0.13

opal

-0.13

rit

-0.13

iances

-0.13

 same

-0.13

POSITIVE LOGITS

/all

0.22

place

0.19

ones

0.18

osate

0.16

ht

0.15

pon

0.15

apr

0.15

ildo

0.14

hw

0.14

sei

0.14

Activations Density 0.066%

references to the quantity or amount of items

No Comments

No Known Activations