INDEX

Explanations

phrases related to conditions and eligibility criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ÃŁ

-0.16

zes

-0.16

 focal

-0.15

front

-0.15

veau

-0.15

uo

-0.14

æŁ

-0.14

 Canc

-0.14

hee

-0.14

ze

-0.14

POSITIVE LOGITS

Ð¸ÑģÐ»Ð¾Ð²

0.18

 conditions

0.18

idot

0.17

conditions

0.17

wahl

0.17

 availability

0.16

nish

0.16

 condition

0.16

æĿ¡ä»¶

0.16

 luck

0.15

Activations Density 0.034%

phrases related to conditions and eligibility criteria

No Comments

No Known Activations