INDEX

Explanations

references to students and student-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

cola

-0.18

byter

-0.17

ball

-0.16

fits

-0.16

.UIManager

-0.15

igit

-0.15

apg

-0.15

adir

-0.15

uges

-0.14

ĶåĽŀ

-0.14

POSITIVE LOGITS

hood

0.19

opleft

0.18

-parent

0.16

enberg

0.16

PointerException

0.16

alker

0.15

ified

0.15

cipher

0.15

urma

0.15

UFFIX

0.15

Activations Density 0.051%

references to students and student-related concepts

No Comments

No Known Activations