INDEX

Explanations

concepts related to algorithmic complexity and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ekil

-0.16

ault

-0.16

ico

-0.15

ĸ

-0.15

 human

-0.14

_DUMP

-0.14

emento

-0.14

 Manning

-0.14

 Eisen

-0.13

human

-0.13

POSITIVE LOGITS

IGIN

0.15

ÐµÐ»ÑĸÐ²

0.15

èĳ

0.14

CLUD

0.14

Ð¾Ð¸ÑĤ

0.14

 Freem

0.14

ãĥ³ãĥĸ

0.13

vod

0.13

odi

0.13

 pute

0.13

Activations Density 0.077%

concepts related to algorithmic complexity and data structures

No Comments

No Known Activations