INDEX

Explanations

repeated phrases or structures in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

erc

-0.17

icable

-0.15

anning

-0.15

XXXXXXXX

-0.14

VICE

-0.14

atos

-0.14

ohl

-0.13

dba

-0.13

obre

-0.13

oya

-0.13

POSITIVE LOGITS

 such

0.20

 everywhere

0.19

 king

0.19

 supposed

0.19

 SUCH

0.17

 becoming

0.17

one

0.16

 great

0.16

 meant

0.16

 cool

0.15

Activations Density 0.388%

repeated phrases or structures in sentences

No Comments

No Known Activations