INDEX

Explanations

phrases that indicate ongoing actions or activities involving "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

chas

-0.16

Ã¡h

-0.14

ama

-0.14

_PIPE

-0.14

idge

-0.14

tribution

-0.14

ritos

-0.14

Ø¬ÙĬ

-0.14

jin

-0.14

 Noon

-0.14

POSITIVE LOGITS

 Äĳang

0.19

 simultaneously

0.18

 busy

0.17

neau

0.17

 à¤°à¤¹

0.16

à¸ģà¸³à¸¥

0.16

busy

0.16

æŃ£åľ¨

0.15

Î¯Î½

0.15

--)↵

0.15

Activations Density 0.126%

phrases that indicate ongoing actions or activities involving "you."

No Comments

No Known Activations