INDEX

Explanations

programming constructs and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

RectTransform

-0.15

ENTA

-0.15

 preload

-0.15

è¬

-0.14

atar

-0.14

ibraries

-0.14

ALSE

-0.13

Rib

-0.13

 Lair

-0.13

Sac

-0.13

POSITIVE LOGITS

Above

0.16

 Above

0.15

arella

0.15

 above

0.15

 ******************************************************************************↵

0.15

 Donovan

0.15

nce

0.15

 Hass

0.15

 Britt

0.14

 Normal

0.14

Activations Density 0.048%

programming constructs and syntax elements

No Comments

No Known Activations