INDEX

Explanations

mathematical symbols and notations related to equations and arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ð¾ÑģÑĤÐ°ÑĤ

-0.16

isel

-0.14

åĨ

-0.14

WB

-0.14

estr

-0.13

indr

-0.13

imei

-0.13

Ú©Ø±ÛĮ

-0.13

appa

-0.13

tables

-0.13

POSITIVE LOGITS

decorators

0.17

IfNeeded

0.16

Ð¼ÐµÑĨÑĮ

0.15

aylor

0.14

 Circus

0.14

CTYPE

0.13

Ð¶Ð¸Ð²

0.13

colo

0.13

 cellspacing

0.13

theid

0.13

Activations Density 0.059%

mathematical symbols and notations related to equations and arrays

No Comments

No Known Activations