INDEX

Explanations

the word "should" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

cran

-0.14

Emm

-0.14

 ÐĴÐ°ÑģÐ¸Ð»ÑĮ

-0.13

 Sound

-0.13

gae

-0.13

usat

-0.13

lobber

-0.13

yc

-0.13

ecast

-0.13

 juris

-0.13

POSITIVE LOGITS

odor

0.16

OfClass

0.15

 èĩ

0.14

.returnValue

0.14

 Ø¯ÙĨ

0.14

iÃªu

0.13

ÑĢÐ¾ÑģÑĤ

0.13

Directions

0.13

ableOpacity

0.13

Activations Density 0.008%

the word "should" in various contexts

No Comments

No Known Activations