INDEX

Explanations

instances of class definitions and related type annotations 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

iked

-0.15

Pie

-0.15

lease

-0.14

uku

-0.14

ima

-0.14

erties

-0.14

ØµÙģ

-0.14

 Star

-0.14

ergus

-0.14

uilder

-0.14

POSITIVE LOGITS

osti

0.16

lund

0.15

senal

0.15

/on

0.15

zes

0.14

 ilma

0.14

æĭľ

0.14

Ð½Ð°Ðº

0.14

rios

0.14

vÄĽd

0.13

Activations Density 0.006%

instances of class definitions and related type annotations in code

No Known Activations