INDEX

Explanations

references to venomous snakes and the effects of their bites

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Ð¿Ð¾Ð¶

-0.16

ufs

-0.16

á»¥

-0.15

warf

-0.15

abei

-0.14

 Garn

-0.14

 lumber

-0.14

 garn

-0.14

esteem

-0.14

 nutrient

-0.13

POSITIVE LOGITS

 poison

0.38

 poisonous

0.38

 Poison

0.36

 poisoning

0.33

æ¯Ĵ

0.31

 toxic

0.30

 poisoned

0.30

 toxins

0.29

 deadly

0.28

 Toxic

0.28

Activations Density 0.108%

references to venomous snakes and the effects of their bites

No Known Activations