INDEX

Explanations

specific terms and structure related to organization and classification within technical contexts

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

andle

-0.15

/umd

-0.15

.dex

-0.15

ilik

-0.15

pher

-0.14

andas

-0.14

iquÃ©

-0.14

inent

-0.14

asonry

-0.14

abyrin

-0.14

POSITIVE LOGITS

Ins

0.22

side

0.21

Ins

0.19

-ins

0.19

ins

0.19

-side

0.19

 side

0.19

ins

0.18

 insulin

0.18

.ins

0.17

Activations Density 0.031%

specific terms and structure related to organization and classification within technical contexts

No Comments

No Known Activations