INDEX

Explanations

programming constructs related to data structures and message handling in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ovny

-0.18

ehler

-0.15

GLOBALS

-0.15

alink

-0.15

lection

-0.14

akov

-0.14

uom

-0.14

asje

-0.14

mps

-0.14

meli

-0.14

POSITIVE LOGITS

 UNUSED

0.17

0.15

ìĿ´ìĸ´

0.14

arg

0.14

 ByVal

0.14

 const

0.14

illard

0.14

riers

0.14

0.13

Activations Density 0.043%

programming constructs related to data structures and message handling in code

No Comments

No Known Activations