INDEX

Explanations

keywords related to specific medical or scientific terms and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

of

-0.42

et

-0.38

oft

-0.37

-0.36

er

-0.35

erver

-0.34

ev

-0.34

on

-0.32

eb

-0.32

oz

-0.32

POSITIVE LOGITS

ãģªãĤĭ

0.16

erving

0.16

orption

0.15

dub

0.15

ourcing

0.15

olutely

0.15

chrift

0.15

ized

0.15

plits

0.15

Activations Density 0.606%

keywords related to specific medical or scientific terms and entities

No Comments

No Known Activations