INDEX

Explanations

dates and references to time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

yms

-0.15

ze

-0.15

zyst

-0.14

ç¿¼

-0.14

 toler

-0.14

fre

-0.14

ieves

-0.14

quare

-0.14

erne

-0.14

Ã©o

-0.14

POSITIVE LOGITS

hora

0.23

Sep

0.23

sep

0.20

-Sep

0.20

.sep

0.20

Sep

0.19

hard

0.18

ARATION

0.18

sep

0.17

hr

0.17

Activations Density 0.013%

dates and references to time

No Comments

No Known Activations