INDEX

Explanations

technical annotations and parameters in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

éłĵ

-0.17

_ioctl

-0.15

lady

-0.15

illard

-0.15

ought

-0.14

oeff

-0.14

Ð¸Ð½ÐºÑĥ

-0.14

border

-0.14

 Hast

-0.14

 border

-0.14

POSITIVE LOGITS

bish

0.17

bjerg

0.16

/Foundation

0.14

ìĤ¬íķŃ

0.14

å¼ķ

0.13

aturated

0.13

 reverse

0.13

tÃ¼

0.13

 cres

0.13

Activations Density 0.008%

technical annotations and parameters in code documentation

No Comments

No Known Activations