INDEX

Explanations

elements that connect disparate ideas or express simplicity and interconnectedness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ugas

-0.16

issant

-0.16

.bd

-0.16

âĢĮØ´Ø¯Ùĩ

-0.16

imal

-0.15

Localized

-0.15

 Reign

-0.15

elly

-0.14

ope

-0.14

ceed

-0.14

POSITIVE LOGITS

ev

0.16

 region

0.16

 area

0.15

rh

0.15

 distance

0.15

Bob

0.14

éĸĵãģ«

0.14

Capture

0.13

Activations Density 0.008%

elements that connect disparate ideas or express simplicity and interconnectedness

No Comments

No Known Activations