INDEX

Explanations

references to specific locations or areas

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

ivant

-0.15

åĸ¶

-0.14

istrov

-0.14

orie

-0.14

yleft

-0.14

iaux

-0.14

kening

-0.13

.instant

-0.13

caf

-0.13

POSITIVE LOGITS

 ÙħØ¨Ø§Ø´

0.15

baugh

0.14

 CORPOR

0.14

OLON

0.13

à¸ķà¸Ļ

0.13

FK

0.13

olson

0.13

VK

0.13

@nate

0.13

KBS

0.13

Activations Density 0.136%

references to specific locations or areas

No Comments

No Known Activations