INDEX

Explanations

the word "like" and its variations in different contexts

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

ucc

-0.19

ccione

-0.16

ÙĤØ§ÙĦ

-0.14

á»ģn

-0.14

 Promise

-0.13

\brief

-0.13

tesy

-0.13

essel

-0.13

anzi

-0.13

uum

-0.13

POSITIVE LOGITS

allen

0.17

eral

0.14

.fast

0.14

neh

0.14

CEE

0.14

contra

0.14

AutoSize

0.13

alytics

0.13

adem

0.13

rox

0.13

Activations Density 0.018%

the word "like" and its variations in different contexts

No Comments

No Known Activations