INDEX

Explanations

symbols frequently used in programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ning

-0.20

ned

-0.16

à¸ķ

-0.15

ÏĦÏĮ

-0.15

/or

-0.15

-0.14

inges

-0.14

sg

-0.14

"path

-0.14

POSITIVE LOGITS

ppers

0.18

ATRIX

0.16

iliz

0.16

/Core

0.15

iness

0.15

 Riding

0.15

adero

0.15

 endl

0.15

anford

0.15

rightness

0.14

Activations Density 0.028%

symbols frequently used in programming or coding contexts

No Comments

No Known Activations