INDEX

Explanations

patterns related to code syntax and formatting

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

ŀ

-0.17

enberg

-0.15

arella

-0.14

illa

-0.14

{}",

-0.14

avage

-0.14

ãĥĨãĥ«

-0.14

 diffÃ©

-0.14

escort

-0.14

ãĥ³ãĥĨãĤ£

-0.14

POSITIVE LOGITS

+]

0.24

?]

0.18

!]

0.17

![

0.17

.]

0.17

pii

0.17

++]

0.17

tes

0.16

ICODE

0.16

oli

0.15

Activations Density 0.078%

patterns related to code syntax and formatting

No Comments

No Known Activations