INDEX

Explanations

programming-related terminology and coding concepts

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

 eslint

-0.16

Inject

-0.15

dict

-0.15

undef

-0.15

.lua

-0.14

 dict

-0.14

åĪº

-0.13

 Michel

-0.13

Ing

-0.13

 KeyError

-0.13

POSITIVE LOGITS

 java

0.32

 Java

0.30

.java

0.28

/java

0.26

Java

0.26

java

0.26

(java

0.25

jav

0.25

_java

0.25

 Collections

0.24

Activations Density 0.061%

programming-related terminology and coding concepts

No Comments

No Known Activations