INDEX

Explanations

structural elements and references in figures and tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

rint

-0.15

ulp

-0.15

Ð°ÑģÑģ

-0.14

ahu

-0.14

æĮĻ

-0.14

ante

-0.14

Luc

-0.13

ButtonItem

-0.13

Mur

-0.13

ahr

-0.13

POSITIVE LOGITS

 caption

0.25

caption

0.24

 Caption

0.23

-caption

0.22

Caption

0.20

hsi

0.18

.caption

0.17

Legend

0.17

 Legend

0.16

 captions

0.16

Activations Density 0.022%

structural elements and references in figures and tables

No Comments

No Known Activations