INDEX

Explanations

numerical values or counts associated with events or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

olf

-0.16

ware

-0.15

ãģ¤ãģ¶

-0.15

udas

-0.15

Contents

-0.15

éĸĵ

-0.15

ellan

-0.14

ICA

-0.14

ica

-0.14

oreach

-0.14

POSITIVE LOGITS

InBackground

0.17

 Jewel

0.15

gings

0.14

ihan

0.14

 à¤§

0.14

chedulers

0.13

.gradle

0.13

gent

0.13

lle

0.13

tti

0.13

Activations Density 0.003%

numerical values or counts associated with events or measurements

No Comments

No Known Activations