INDEX

Explanations

references to data structures or elements commonly used in programming and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.16

ikip

-0.15

enderit

-0.15

bl

-0.15

æĬĺ

-0.14

 chim

-0.14

biz

-0.14

aver

-0.14

ucket

-0.14

POSITIVE LOGITS

 Deng

0.15

.until

0.15

ebi

0.15

å§ī

0.14

uen

0.14

ince

0.14

ÏģÎ¯

0.14

eny

0.14

Dod

0.14

UNDLE

0.14

Activations Density 0.035%

references to data structures or elements commonly used in programming and libraries

No Comments

No Known Activations