INDEX

Explanations

variations of the word "sap."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ey

-0.19

er

-0.18

hod

-0.18

iams

-0.17

hq

-0.17

atr

-0.16

hoff

-0.16

 Honey

-0.16

-0.15

POSITIVE LOGITS

pling

0.24

ìŀĲê¸°

0.22

pler

0.21

erture

0.20

pearance

0.20

dragon

0.20

plied

0.20

ital

0.20

pliance

0.19

oose

0.18

Activations Density 0.041%

variations of the word "sap."

No Comments

No Known Activations