INDEX

Explanations

instances of high-impact statements or declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.17

 Slater

-0.16

rand

-0.14

erland

-0.14

arti

-0.14

 Mish

-0.14

rs

-0.14

ALE

-0.13

bot

-0.13

kiem

-0.13

POSITIVE LOGITS

igu

0.15

BoundingClientRect

0.15

ìĦľ

0.15

.scalablytyped

0.15

aned

0.14

 Wend

0.14

ota

0.14

etine

0.14

.Link

0.14

enderit

0.14

Activations Density 0.149%

instances of high-impact statements or declarations

No Comments

No Known Activations