INDEX

Explanations

HTML and layout-related elements within a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aad

-0.16

atÃ³

-0.15

dateFormat

-0.14

æ±

-0.14

.touches

-0.14

ÏĥÏĦÎ±Î½

-0.14

 Ð´Ñĥ

-0.14

ÐµÐ½ÐºÐ°

-0.13

 textDecoration

-0.13

 Lund

-0.13

POSITIVE LOGITS

 offset

0.21

col

0.20

 offsets

0.19

offset

0.18

Col

0.18

-md

0.18

Co

0.18

 Offset

0.17

col

0.17

Col

0.17

Activations Density 0.010%

HTML and layout-related elements within a coding context

No Comments

No Known Activations