INDEX

Explanations

HTML and JavaScript code snippets, particularly focusing on type attributes and CDATA sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aket

-0.18

iske

-0.15

notated

-0.14

áº«

-0.14

ords

-0.14

peak

-0.14

iment

-0.14

/environment

-0.13

ysz

-0.13

Mui

-0.13

POSITIVE LOGITS

sop

0.15

arten

0.15

PostalCodes

0.14

obo

0.14

Hed

0.14

èĽĽ

0.14

 Yates

0.13

utherland

0.13

Ø§ØªØ±

0.13

_MATH

0.13

Activations Density 0.003%

HTML and JavaScript code snippets, particularly focusing on type attributes and CDATA sections

No Comments

No Known Activations