INDEX

Explanations

occurrences of the word "new."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

arine

-0.17

 close

-0.16

ipse

-0.16

 trom

-0.16

 closely

-0.15

 peer

-0.14

 Close

-0.13

Close

-0.13

roller

-0.13

intern

-0.13

POSITIVE LOGITS

ceph

0.17

oya

0.14

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

0.14

layan

0.14

LOW

0.14

.infinity

0.14

æŀľ

0.14

egg

0.14

ateria

0.14

atego

0.13

Activations Density 0.064%

occurrences of the word "new."

No Comments

No Known Activations