INDEX

Explanations

phrases that involve the concept of "ideas" or "thoughts."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ply

-0.16

ych

-0.16

((-

-0.15

hol

-0.14

elay

-0.14

QT

-0.14

 notice

-0.14

 sede

-0.14

uÃ©

-0.14

ium

-0.13

POSITIVE LOGITS

Ãłng

0.18

erif

0.16

Ð¾ÑĪ

0.16

rlen

0.15

ãĥ³ãĤº

0.15

StackNavigator

0.15

ãĥ³ãĤ¹

0.14

GetInt

0.14

ÙĦÙħÙĩ

0.14

leck

0.14

Activations Density 0.034%

phrases that involve the concept of "ideas" or "thoughts."

No Comments

No Known Activations