INDEX

Explanations

interrogative phrases and expressions of uncertainty or concern

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

 discontin

-0.17

 deadlock

-0.15

Ø§ÙĩØ§

-0.15

fet

-0.15

 Schneider

-0.14

uga

-0.14

_DEN

-0.14

Lab

-0.14

otty

-0.14

oggles

-0.14

POSITIVE LOGITS

 loss

0.25

 Loss

0.23

loss

0.22

 losses

0.22

Loss

0.21

lose

0.20

_loss

0.20

 losing

0.20

 Losing

0.20

.loss

0.20

Activations Density 0.010%

interrogative phrases and expressions of uncertainty or concern

No Comments

No Known Activations