INDEX

Explanations

the word "na" and its variations, likely searching for occurrences of a specific name or reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ends

-0.15

 Ð¿ÐµÑĢÐµÑĢ

-0.15

neys

-0.14

rible

-0.14

Ã¤tt

-0.14

Ã¤ter

-0.14

grÃ©

-0.14

aho

-0.13

ei

-0.13

gren

-0.13

POSITIVE LOGITS

utilus

0.23

ive

0.22

ught

0.20

ughty

0.20

ively

0.19

omi

0.18

idos

0.17

erosis

0.17

issance

0.17

IVE

0.16

Activations Density 0.023%

the word "na" and its variations, likely searching for occurrences of a specific name or reference

No Comments

No Known Activations