INDEX

Explanations

instances of specific abbreviations or acronyms, particularly in a medical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ä°Y

-0.16

VILLE

-0.16

.infinity

-0.15

é¹¿

-0.15

 Extreme

-0.15

akter

-0.14

weet

-0.14

aliz

-0.14

active

-0.14

 bols

-0.14

POSITIVE LOGITS

ilion

0.30

lov

0.22

illion

0.22

illon

0.21

ilon

0.20

ements

0.19

ement

0.19

itra

0.18

pav

0.18

imenti

0.18

Activations Density 0.007%

instances of specific abbreviations or acronyms, particularly in a medical context

No Comments

No Known Activations