INDEX

Explanations

references to programming functions and routines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

xn

-0.17

liÄį

-0.16

itionally

-0.15

owan

-0.15

elian

-0.15

ullo

-0.15

icture

-0.15

ollo

-0.14

åĴ

-0.14

amping

-0.14

POSITIVE LOGITS

erdale

0.16

eryl

0.15

 stim

0.14

ForRow

0.14

bows

0.14

ê¸°ìĹĲ

0.13

.shtml

0.13

 Weiss

0.13

ajor

0.13

 mech

0.13

Activations Density 0.006%

references to programming functions and routines

No Comments

No Known Activations