INDEX

Explanations

words related to classification and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

atten

-0.17

Gab

-0.15

ãĥ¼ãĤ¸

-0.15

oux

-0.15

 Caldwell

-0.15

wu

-0.14

enant

-0.14

æŃ©

-0.14

 replacements

-0.14

 Lace

-0.13

POSITIVE LOGITS

æīĢå±ŀ

0.23

 Placement

0.18

 placement

0.18

 Into

0.17

 sorting

0.17

 into

0.17

å½Ĵ

0.17

ategories

0.16

.categories

0.16

 categor

0.15

Activations Density 0.232%

words related to classification and categorization

No Comments

No Known Activations