INDEX

Explanations

phrases and terms indicating costs or value judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

.googlecode

-0.16

yps

-0.15

 Downs

-0.15

atel

-0.14

ctors

-0.14

 Wonder

-0.14

ÑıÐ½

-0.14

à¸ģà¸ķ

-0.14

ekten

-0.14

itur

-0.13

POSITIVE LOGITS

auth

0.27

 authentic

0.26

 Stitch

0.26

 Authentic

0.26

 outlet

0.25

/Auth

0.25

.auth

0.25

jer

0.25

 auth

0.24

Auth

0.24

Activations Density 0.031%

phrases and terms indicating costs or value judgments

No Comments

No Known Activations