INDEX

Explanations

words related to medical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

alach

-0.19

kode

-0.17

icks

-0.16

ish

-0.16

aur

-0.15

kas

-0.15

ische

-0.15

ischen

-0.15

iest

-0.14

aspect

-0.14

POSITIVE LOGITS

heck

0.26

chio

0.26

embre

0.25

idal

0.23

illin

0.22

 acid

0.22

raft

0.22

ourt

0.21

 heck

0.21

cio

0.21

Activations Density 0.094%

words related to medical terminology

No Comments

No Known Activations