INDEX

Explanations

references to the reader's involvement or relationship with the content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 themselves

-0.22

 usted

-0.19

igation

-0.15

lÃŃ

-0.15

 himself

-0.15

iol

-0.14

ycz

-0.14

 YaÅŁ

-0.14

Ú¯Ø§Ùĩ

-0.14

Lag

-0.14

POSITIVE LOGITS

 yourself

0.29

 guys

0.28

nger

0.28

’re

0.24

ths

0.23

're

0.22

-mÃªme

0.20

nge

0.20

essler

0.19

SELF

0.19

Activations Density 0.663%

references to the reader's involvement or relationship with the content

No Comments

No Known Activations