INDEX

Explanations

terms related to laboratory safety and regulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

adele

-0.17

ingu

-0.16

Ple

-0.15

exion

-0.15

iale

-0.15

Sob

-0.15

iji

-0.15

acias

-0.15

illa

-0.14

idge

-0.14

POSITIVE LOGITS

utom

0.14

geÃ§

0.14

.fil

0.14

Ð¾ÑĢÐ°Ñı

0.14

onte

0.14

Ã³wn

0.13

#line

0.13

bas

0.13

ully

0.13

tsy

0.13

Activations Density 0.001%

terms related to laboratory safety and regulation

No Comments

No Known Activations