INDEX

Explanations

elements and attributes related to programming or coding constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

gress

-0.15

jos

-0.15

 tran

-0.14

ÐµÐ²Ð¸Ð´

-0.14

ÐµÐµ

-0.14

mint

-0.13

 Trans

-0.13

seg

-0.13

syn

-0.13

gang

-0.13

POSITIVE LOGITS

inton

0.16

raj

0.14

iye

0.14

izin

0.14

 Hernandez

0.14

Ø§Ø²ÙĬ

0.14

/gtest

0.14

 Ãºn

0.13

-placeholder

0.13

 Hern

0.13

Activations Density 0.052%

elements and attributes related to programming or coding constructs

No Comments

No Known Activations