INDEX

Explanations

instances of the word "in" as well as other programming keywords related to loops and data structures

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

lein

-0.16

ÌĨ

-0.15

 none

-0.14

ROTO

-0.14

 Ð²Ð½ÐµÑģ

-0.14

faith

-0.14

ãĥ¬ãĥĵ

-0.14

Ø§Ø±Ø§ÙĨ

-0.13

Ð¸ÐºÐ¸

-0.13

ow

-0.13

POSITIVE LOGITS

 reversed

0.18

 range

0.17

erator

0.16

 tqdm

0.15

errat

0.15

 enumerate

0.14

mgr

0.14

ortal

0.14

oenix

0.14

 GetAll

0.14

Activations Density 0.048%

instances of the word "in" as well as other programming keywords related to loops and data structures

No Comments

No Known Activations