INDEX

Explanations

contrasts between past and present experiences or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 overseas

-0.15

zell

-0.14

Ana

-0.14

 Boards

-0.14

opic

-0.14

ãĥ³ãĤ¹

-0.14

 snatch

-0.14

 Heap

-0.14

edom

-0.14

Īĺ

-0.13

POSITIVE LOGITS

otch

0.19

phin

0.18

ï»¿#

0.16

ignal

0.16

ÑĤÐ¾Ñĩ

0.16

é¨

0.16

 ultimately

0.15

aight

0.15

.wordpress

0.15

SWEP

0.14

Activations Density 0.195%

contrasts between past and present experiences or states

No Comments

No Known Activations