INDEX

Explanations

verbs associated with exploration or deep engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.20

Expiration

-0.17

-0.15

angs

-0.15

ech

-0.15

rej

-0.15

achuset

-0.14

gal

-0.14

askan

-0.14

POSITIVE LOGITS

ustr

0.17

onica

0.15

anca

0.14

egrator

0.14

ertz

0.14

arker

0.14

 Ying

0.13

 LATIN

0.13

anco

0.13

uria

0.13

Activations Density 0.026%

verbs associated with exploration or deep engagement

No Comments

No Known Activations