INDEX

Explanations

significant numerical values and quantifiable concepts

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

upal

-0.16

patch

-0.16

uet

-0.15

plr

-0.14

 áº¢

-0.14

 Jacqu

-0.14

obe

-0.14

 Powder

-0.14

ix

-0.14

Ð»ÐµÐ²

-0.14

POSITIVE LOGITS

kom

0.15

accordion

0.15

ughs

0.14

czy

0.14

lesi

0.13

combe

0.13

áº¬

0.13

erase

0.13

ĮĢ

0.13

kening

0.13

Activations Density 0.032%

significant numerical values and quantifiable concepts

No Comments

No Known Activations

significant numerical values and quantifiable concepts

No Comments

No Known Activations