INDEX

Explanations

expressions related to emotional engagement and reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

acher

-0.17

 negot

-0.15

.Startup

-0.15

hec

-0.15

æ¼«

-0.14

Ã³r

-0.14

adamente

-0.14

 znam

-0.14

Rak

-0.14

egers

-0.13

POSITIVE LOGITS

awe

0.33

 speech

0.29

 impressed

0.28

 blown

0.28

 spell

0.27

 capt

0.25

 Speech

0.25

 fasc

0.25

 wonder

0.24

Speech

0.24

Activations Density 0.361%

expressions related to emotional engagement and reactions

No Comments

No Known Activations