INDEX

Explanations

expressions of loss and remembrance of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

omer

-0.16

INGTON

-0.15

 Authority

-0.15

ington

-0.14

ald

-0.14

ince

-0.13

ImageUrl

-0.13

PMC

-0.13

ÃŃg

-0.13

omers

-0.13

POSITIVE LOGITS

 wonderful

0.32

 great

0.27

 lovely

0.25

 amazing

0.25

 beautiful

0.23

 incredible

0.22

 fantastic

0.22

 dedicated

0.21

 extraordinary

0.21

 dear

0.21

Activations Density 0.310%

expressions of loss and remembrance of individuals

No Comments

No Known Activations