INDEX

Explanations

phrases related to eligibility and conditions in agreements or offers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ollo

-0.18

agne

-0.16

veau

-0.15

loff

-0.15

rias

-0.15

lok

-0.15

Inlining

-0.14

rente

-0.14

abar

-0.14

orde

-0.14

POSITIVE LOGITS

 conditions

0.19

æĿ¡ä»¶

0.18

 condition

0.17

 condi

0.16

ÃĽ

0.16

 veter

0.15

 ÑĥÑģÐ»

0.15

sdale

0.14

 Conditions

0.14

sgi

0.14

Activations Density 0.024%

phrases related to eligibility and conditions in agreements or offers

No Comments

No Known Activations