INDEX

Explanations

code elements and assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Å¸

-0.16

ickerView

-0.16

lein

-0.15

hait

-0.14

 Giov

-0.14

itele

-0.14

Miy

-0.14

zo

-0.14

ellig

-0.14

 tslint

-0.13

POSITIVE LOGITS

 require

0.15

erek

0.15

 Sand

0.14

orp

0.14

 Albert

0.14

NullOrEmpty

0.14

 umbrella

0.13

.Record

0.13

adin

0.13

ales

0.13

Activations Density 0.035%

code elements and assignments

No Comments

No Known Activations