INDEX

Explanations

mathematical notations and symbols, particularly those related to sets and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

eper

-0.17

inverse

-0.16

uÃ©

-0.16

-0.15

olini

-0.15

 mortar

-0.14

afone

-0.14

^[

-0.14

yn

-0.14

POSITIVE LOGITS

0.26

akers

0.16

{T

0.16

htt

0.15

{_

0.15

asm

0.15

ak

0.15

0.14

krv

0.14

aky

0.14

Activations Density 0.027%

mathematical notations and symbols, particularly those related to sets and operations

No Comments

No Known Activations