INDEX

Explanations

keywords and identifiers commonly used in programming and technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

IGH

-0.15

igar

-0.15

__,__

-0.15

icher

-0.15

 contrario

-0.14

ENO

-0.14

igham

-0.14

umar

-0.14

ilst

-0.14

otte

-0.13

POSITIVE LOGITS

buz

0.15

Placement

0.14

 Brewery

0.14

plets

0.14

outh

0.14

 amen

0.14

 leveling

0.13

stants

0.13

 placement

0.13

Activations Density 0.051%

keywords and identifiers commonly used in programming and technical documents

No Comments

No Known Activations