INDEX

Explanations

references to homework and academic assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

kest

-0.17

oe

-0.16

estring

-0.15

zin

-0.15

Ð¾Ð³ÑĢÐ°Ð¼

-0.14

æ¡Ĳ

-0.13

ButtonModule

-0.13

iese

-0.13

_BINARY

-0.13

ÑĢÑĥÐ·

-0.13

POSITIVE LOGITS

ÑĢÐ´

0.15

insic

0.15

andr

0.15

afen

0.15

adel

0.14

ìĪĻ

0.14

adr

0.14

af

0.14

Ð¸Ð½Ð¸

0.14

à¸£

0.13

Activations Density 0.032%

references to homework and academic assignments

No Comments

No Known Activations