INDEX

Explanations

conditional statements and logical operators 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 @ 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

eger

-0.15

.joda

-0.14

 setattr

-0.14

malloc

-0.14

ä¸įäºĨ

-0.14

.obtain

-0.13

íĨłíĨł

-0.13

 notifyDataSetChanged

-0.13

esz

-0.13

_mk

-0.13

POSITIVE LOGITS

!(

0.23

0.22

Is

0.22

 isinstance

0.22

 (↵

0.21

 should

0.20

is

0.20

 contains

0.19

!"

0.18

is

0.18

Activations Density 0.265%

conditional statements and logical operators in code

No Comments

No Known Activations