INDEX

Explanations

references to medical professionals, specifically doctors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ened

-0.17

gio

-0.16

ennon

-0.15

riters

-0.15

ens

-0.15

raf

-0.15

elite

-0.14

ed

-0.14

ende

-0.14

olic

-0.14

POSITIVE LOGITS

aper

0.22

isc

0.22

iven

0.21

inking

0.20

infeld

0.20

hab

0.20

ifting

0.19

Dr

0.19

illing

0.18

utex

0.18

Activations Density 0.034%

references to medical professionals, specifically doctors

No Comments

No Known Activations