INDEX

Explanations

instances of explosive or sudden actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

izr

-0.16

nez

-0.16

ifax

-0.15

Ø·Ø±

-0.15

á»ĩ

-0.15

ÐµÑĢÑĤ

-0.15

rai

-0.15

andum

-0.14

umin

-0.14

ibe

-0.14

POSITIVE LOGITS

 burst

0.21

 Burst

0.21

 bursts

0.19

 into

0.18

 bursting

0.18

çĤ¸

0.18

burst

0.17

 forth

0.17

implode

0.16

0.15

Activations Density 0.048%

instances of explosive or sudden actions

No Comments

No Known Activations