INDEX

Explanations

words and phrases related to administrative functions or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ings

-0.19

çİĩ

-0.16

uw

-0.15

ogne

-0.15

INGS

-0.15

Ø§ÙĨØ¯

-0.15

ãģĴ

-0.15

 Pare

-0.14

ogene

-0.14

Ø¨Ø§ÙĨ

-0.14

POSITIVE LOGITS

stration

0.33

istrar

0.28

ister

0.25

ISTRATION

0.25

ISTR

0.24

-ajax

0.24

isters

0.24

istrator

0.24

istration

0.23

instr

0.23

Activations Density 0.021%

words and phrases related to administrative functions or roles

No Comments

No Known Activations