INDEX

Explanations

elements related to coding or programming commands and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

kah

-0.15

ANCH

-0.15

ãĤ¹ãĥŀ

-0.14

VOKE

-0.14

å¯

-0.14

elic

-0.14

çłĤ

-0.14

tt

-0.13

__;↵

-0.13

POSITIVE LOGITS

ìĨĶ

0.16

 Osman

0.15

Ð¾Ð·Ð°

0.15

stdClass

0.15

Siz

0.15

æŀľ

0.15

ãĤ¯ãĤ»

0.14

BeginInit

0.14

ADB

0.14

à¸¸à¹Ī

0.14

Activations Density 0.065%

elements related to coding or programming commands and parameters

No Comments

No Known Activations