INDEX

Explanations

references to personal experiences and professional roles

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

oure

-0.17

 BuzzFeed

-0.16

ophobia

-0.15

Ø®Ø§ÙĨÙĩ

-0.15

quina

-0.15

perse

-0.15

iei

-0.14

ja

-0.14

 anon

-0.14

ãĤ²

-0.14

POSITIVE LOGITS

 personal

0.23

personal

0.19

 Personal

0.17

Personal

0.17

 personally

0.16

ugar

0.16

Ãłn

0.15

/self

0.14

 kiÅŁisel

0.14

à¹Ĥà¸Ĭ

0.14

Activations Density 0.062%

references to personal experiences and professional roles

No Comments

No Known Activations