INDEX

Explanations

references to maps and mapping concepts

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

utom

-0.19

iosa

-0.18

ifr

-0.18

naire

-0.16

hood

-0.16

éĥİ

-0.16

ä¿Ĺ

-0.15

typed

-0.15

ioso

-0.14

ueur

-0.14

POSITIVE LOGITS

illary

0.18

.ObjectMapper

0.17

YRO

0.17

reuse

0.17

åĥıæĺ¯

0.16

AZY

0.15

.writeValue

0.15

alama

0.14

reduce

0.14

riter

0.14

Activations Density 0.032%

references to maps and mapping concepts

No Comments

No Known Activations