INDEX

Explanations

terms related to associations or groupings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oby

-0.18

rah

-0.17

æİª

-0.17

eres

-0.17

cape

-0.16

zeug

-0.16

onas

-0.15

ening

-0.15

vis

-0.15

pon

-0.15

POSITIVE LOGITS

endir

0.22

/group

0.18

SHIP

0.17

iaz

0.17

ductive

0.16

iaÃ§Ã£o

0.15

adaÅŁ

0.15

RICS

0.15

ive

0.15

Activations Density 0.035%

terms related to associations or groupings

No Comments

No Known Activations