INDEX

Explanations

variations of the word "understanding" 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

azon

-0.18

rone

-0.16

allon

-0.16

ouch

-0.15

nett

-0.15

arry

-0.15

usc

-0.14

Ø±ÛĮÙħ

-0.14

aj

-0.14

union

-0.14

POSITIVE LOGITS

ably

0.21

 understanding

0.18

.microsoft

0.17

fulness

0.17

 Understanding

0.16

Understanding

0.16

fully

0.15

igne

0.15

SSION

0.15

erland

0.14

Activations Density 0.043%

variations of the word "understanding" in different contexts

No Comments

No Known Activations