INDEX

Explanations

emotional expressions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 ATTRIBUTE

-0.15

ripe

-0.14

arto

-0.14

IDEO

-0.14

 RECEIVER

-0.13

IPH

-0.13

Dick

-0.13

ENUM

-0.13

olars

-0.13

inen

-0.13

POSITIVE LOGITS

YA

0.23

 Authors

0.22

 AUTHORS

0.22

Ner

0.21

Authors

0.21

 authors

0.20

Na

0.20

 fandom

0.20

YA

0.19

 agents

0.18

Activations Density 0.017%

emotional expressions and experiences

No Comments

No Known Activations