INDEX

Explanations

mathematical notations and symbols in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

andest

-0.18

ez

-0.17

dra

-0.17

aldo

-0.14

ê²¬

-0.14

tk

-0.14

ients

-0.14

rray

-0.13

.cc

-0.13

anka

-0.13

POSITIVE LOGITS

cal

0.25

ematic

0.22

cal

0.22

ieu

0.20

ematics

0.20

bf

0.19

matic

0.16

CAL

0.15

Cal

0.15

rax

0.15

Activations Density 0.032%

mathematical notations and symbols in equations

No Comments

No Known Activations