INDEX

Explanations

phrases that indicate moving forward or continuing with a specific action or plan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

eson

-0.16

cus

-0.16

alach

-0.16

ussed

-0.15

bell

-0.14

ucht

-0.14

going

-0.14

gren

-0.14

gon

-0.14

POSITIVE LOGITS

 with

0.20

 toward

0.18

with

0.18

 dengan

0.17

 vá»Ľi

0.16

swith

0.16

 towards

0.16

ure

0.16

 proced

0.16

 withd

0.15

Activations Density 0.034%

phrases that indicate moving forward or continuing with a specific action or plan

No Comments

No Known Activations