INDEX

Explanations

punctuation and emotional expressions

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

âĸį

-0.19

_Tis

-0.18

USTER

-0.15

_Lean

-0.14

SGlobal

-0.13

itled

-0.13

FileVersion

-0.13

ledged

-0.13

 RELATED

-0.12

ponsored

-0.12

POSITIVE LOGITS

 Fantastic

0.25

.-

0.22

Thanks

0.22

Hi

0.22

thanks

0.21

hi

0.21

 fantastic

0.21

Great

0.21

oo

0.21

HI

0.20

Activations Density 0.020%

punctuation and emotional expressions

No Comments

No Known Activations