INDEX

Explanations

data structure elements and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Wa

-0.16

roperties

-0.15

antz

-0.14

 Peters

-0.14

eid

-0.14

Gut

-0.14

itel

-0.14

 amateurs

-0.14

olly

-0.14

napshot

-0.14

POSITIVE LOGITS

 required

0.23

 Required

0.20

required

0.18

	required

0.18

Required

0.18

 REQUIRED

0.17

MarshalAs

0.17

.required

0.16

-required

0.16

IsRequired

0.16

Activations Density 0.045%

data structure elements and their attributes

No Comments

No Known Activations