INDEX

Explanations

mentions of locations or entities associated with healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Canter

-0.20

-0.16

ÙĪØ±Ø´

-0.16

vio

-0.16

 Barton

-0.15

vise

-0.15

tron

-0.15

erez

-0.15

POSITIVE LOGITS

aryana

0.37

riday

0.25

unar

0.25

aldi

0.23

ARY

0.23

indi

0.23

ary

0.23

oli

0.23

oshi

0.23

iran

0.22

Activations Density 0.012%

mentions of locations or entities associated with healthcare

No Comments

No Known Activations