INDEX

Explanations

statements concerning safety protocols and organizational responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Interview

-0.19

 interview

-0.16

 spoken

-0.16

 Uncomment

-0.15

Interview

-0.15

 dÆ°

-0.14

ordon

-0.14

inp

-0.14

alk

-0.14

Ut

-0.14

POSITIVE LOGITS

 wrote

0.34

 writes

0.31

 write

0.29

 Writes

0.27

writes

0.27

.write

0.26

 reads

0.25

write

0.25

 viáº¿t

0.24

 WRITE

0.23

Activations Density 0.085%

statements concerning safety protocols and organizational responses

No Comments

No Known Activations