INDEX

Explanations

phrases related to saving or preservation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ennen

-0.17

soever

-0.17

gger

-0.15

å¹

-0.15

.contents

-0.14

cale

-0.14

abyrinth

-0.14

ERV

-0.14

 componentDid

-0.14

fram

-0.14

POSITIVE LOGITS

OrUpdate

0.17

ellar

0.17

 saves

0.17

 Saves

0.17

à¤¿à¤·

0.16

icular

0.16

.Save

0.15

gn

0.15

 save

0.15

ÏĦÏīÎ½

0.15

Activations Density 0.053%

phrases related to saving or preservation

No Comments

No Known Activations