INDEX

Explanations

references to historical events or their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

YO

-0.19

raquo

-0.17

awah

-0.16

ebo

-0.16

upro

-0.16

deaux

-0.15

ollah

-0.14

ierten

-0.14

romatic

-0.14

rxjs

-0.14

POSITIVE LOGITS

[:]

0.29

[,]

0.27

[.

0.26

...]

0.24

âĢ¦.

0.23

 [...]

0.23

....

0.23

[,

0.22

 ....

0.22

...]↵↵

0.21

Activations Density 0.753%

references to historical events or their implications

No Comments

No Known Activations