INDEX

Explanations

phrases related to movement or direction, particularly focusing on 'upward' and 'downward' trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oday

-0.17

aceous

-0.17

airie

-0.15

omorphic

-0.15

SELL

-0.15

ELS

-0.14

Ã³ÅĤ

-0.14

ëĿ

-0.14

 Romero

-0.14

POSITIVE LOGITS

.LayoutStyle

0.17

à¸

0.15

mith

0.15

gent

0.15

yw

0.15

lander

0.14

eview

0.14

rias

0.14

rix

0.14

yk

0.14

Activations Density 0.009%

phrases related to movement or direction, particularly focusing on 'upward' and 'downward' trends

No Comments

No Known Activations