INDEX

Explanations

questions about personal preferences and experiences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

trand

-0.15

etto

-0.15

rev

-0.15

eph

-0.15

omo

-0.14

 Haram

-0.14

bur

-0.14

olders

-0.14

osing

-0.14

ussen

-0.14

POSITIVE LOGITS

 Realty

0.16

/stdc

0.16

à¹īà¸Ļà¸Ĺ

0.16

 Gregg

0.15

Ø®Ø¨

0.15

iaux

0.15

ìļķ

0.14

arger

0.14

 componentDid

0.14

lund

0.14

Activations Density 0.442%

questions about personal preferences and experiences

No Known Activations