INDEX

Explanations

specific code elements and SQL-related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etrofit

-0.23

TEGER

-0.23

ItemClickListener

-0.23

rganization

-0.22

irtual

-0.21

HITE

-0.20

ERTICAL

-0.20

gnore

-0.19

olume

-0.19

mployee

-0.19

POSITIVE LOGITS

ccording

0.22

0.21

ftware

0.20

ãĤ£

0.17

mong

0.17

stead

0.17

eer

0.17

sure

0.17

viders

0.16

scriber

0.16

Activations Density 0.085%

specific code elements and SQL-related terms

No Comments

No Known Activations