INDEX

Explanations

terms and phrases related to statistical data or research, particularly in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 TÃ¢n

-0.16

âĢĮØ³ÛĮ

-0.16

ivas

-0.15

emble

-0.14

.multipart

-0.14

vib

-0.14

ider

-0.14

èĶ

-0.13

iva

-0.13

ve

-0.13

POSITIVE LOGITS

_embed

0.17

-P

0.16

ssf

0.16

ÄħÅ¼

0.15

 ethnicity

0.14

kup

0.14

 Contractors

0.14

 Brock

0.14

 Ethnic

0.14

ethnic

0.14

Activations Density 0.015%

terms and phrases related to statistical data or research, particularly in academic contexts

No Comments

No Known Activations