INDEX

Explanations

terms related to waking up or being alert

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.scalablytyped

-0.17

annes

-0.15

hb

-0.15

erosis

-0.14

aines

-0.14

UTO

-0.14

avou

-0.14

éĢŁ

-0.14

áº©u

-0.14

acy

-0.13

POSITIVE LOGITS

 Wake

0.20

/alert

0.19

 wake

0.18

Wake

0.18

oga

0.17

éĨĴ

0.17

chia

0.17

 wakeup

0.17

ihan

0.15

amilia

0.15

Activations Density 0.041%

terms related to waking up or being alert

No Comments

No Known Activations