INDEX

Explanations

references to entities or individuals, particularly focusing on their characteristics and contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 lÃł

-0.17

Ã©k

-0.15

æĺ¯ä¸ª

-0.15

.Absolute

-0.14

ignKey

-0.14

 themselves

-0.14

edException

-0.14

_tA

-0.14

OrUpdate

-0.13

_tD

-0.13

POSITIVE LOGITS

ä¸Ķ

0.18

zo

0.16

 withd

0.15

 worth

0.15

Ð½ÐµÐ´

0.14

asin

0.14

 deserves

0.13

chten

0.13

illac

0.13

 Leer

0.13

Activations Density 0.138%

references to entities or individuals, particularly focusing on their characteristics and contributions

No Comments

No Known Activations