INDEX

Explanations

conditional statements related to uncertainty or possibility

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

@dynamic

-0.18

usz

-0.17

ãĥ¡ãĥ³ãĥĪ

-0.16

iller

-0.16

iday

-0.16

æķ¢

-0.15

áº¹p

-0.15

toy

-0.15

ãĥĢãĤ¤

-0.14

Æ°á»

-0.14

POSITIVE LOGITS

alim

0.17

kle

0.16

 interpret

0.14

 another

0.14

bis

0.13

asic

0.13

 McGregor

0.13

anger

0.13

 salv

0.13

Activations Density 0.020%

conditional statements related to uncertainty or possibility

No Comments

No Known Activations