INDEX

Explanations

words related to medical emergencies and poison ingestion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

unca

-0.15

èĤ©

-0.14

 æľĿ

-0.14

èĻŁ

-0.14

weg

-0.14

uchos

-0.13

pev

-0.13

scar

-0.13

fork

-0.13

 Hanson

-0.13

POSITIVE LOGITS

 poisoning

0.29

 Poison

0.26

 ingestion

0.25

 toxic

0.24

 toxicity

0.24

 poison

0.24

 antid

0.24

 overdose

0.23

 Toxic

0.23

 poisonous

0.23

Activations Density 0.077%

words related to medical emergencies and poison ingestion

No Comments

No Known Activations