INDEX

Explanations

terms related to chemistry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arian

-0.18

olik

-0.15

thead

-0.15

osate

-0.15

NORMAL

-0.15

able

-0.14

pcf

-0.14

 Broadcasting

-0.14

ookie

-0.14

angs

-0.14

POSITIVE LOGITS

istry

0.27

ISTRY

0.26

ICAL

0.25

ical

0.24

ically

0.23

trail

0.22

istr

0.20

 trails

0.20

icals

0.20

ometrics

0.19

Activations Density 0.007%

terms related to chemistry

No Comments

No Known Activations