INDEX

Explanations

the word "easily" and related forms indicating simplicity or accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ively

-0.17

ÐµÐ´Ð¸Ð½

-0.16

.scalablytyped

-0.15

 Sawyer

-0.15

igans

-0.14

mers

-0.13

akedirs

-0.13

 wonders

-0.13

 Ð¿Ð¾Ð»ÑĮÐ·

-0.13

POSITIVE LOGITS

 dÃłng

0.33

going

0.22

-access

0.20

forgettable

0.17

accessible

0.17

 accessible

0.17

mente

0.17

dismiss

0.16

sez

0.16

-medium

0.16

Activations Density 0.017%

the word "easily" and related forms indicating simplicity or accessibility

No Comments

No Known Activations