INDEX

Explanations

terms related to laboratory safety and disease prevention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ãĤ¹ãĥ¬

-0.15

hub

-0.14

lu

-0.14

éĿł

-0.14

ilib

-0.14

nten

-0.14

tual

-0.14

aji

-0.14

trak

-0.13

Ð°Ð

-0.13

POSITIVE LOGITS

 Humans

0.23

/*

0.20

Humans

0.19

 Female

0.17

pone

0.17

 humans

0.17

/stat

0.16

 Animals

0.16

Female

0.15

/class

0.15

Activations Density 0.009%

terms related to laboratory safety and disease prevention

No Comments

No Known Activations