INDEX

Explanations

terms related to pharmacology and related fields

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

ÑıÑģ

-0.15

 Stefan

-0.13

ibern

-0.13

 Provid

-0.13

loh

-0.13

ropol

-0.13

rotch

-0.13

[]={

-0.13

ocator

-0.13

otron

-0.13

POSITIVE LOGITS

/ph

0.21

aceutical

0.20

aceut

0.19

 Pharm

0.18

okin

0.18

acist

0.17

 èĤ

0.16

privileged

0.16

uffix

0.15

 pharm

0.15

Activations Density 0.014%

terms related to pharmacology and related fields

No Comments

No Known Activations