INDEX

Explanations

references to object-oriented programming concepts, particularly involving 'self' and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

	TokenName

-0.15

readcr

-0.15

jar

-0.14

 Tome

-0.14

aga

-0.14

ScrollIndicator

-0.13

viders

-0.13

ockey

-0.13

ãĤº

-0.13

Ã½

-0.13

POSITIVE LOGITS

 expectations

0.39

 expect

0.38

 expectation

0.37

 Expect

0.36

 assertEquals

0.35

expect

0.33

 EXPECT

0.33

 expecting

0.32

 assertTrue

0.31

Expect

0.31

Activations Density 0.004%

references to object-oriented programming concepts, particularly involving 'self' and function definitions

No Comments

No Known Activations