INDEX

Explanations

phrases indicating a specific timeframe or context in the writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

eph

-0.13

 Overall

-0.13

ouv

-0.13

 ansch

-0.12

ouis

-0.12

jah

-0.12

Overall

-0.12

ucch

-0.12

 overall

-0.12

Ä±ÅŁma

-0.12

POSITIVE LOGITS

 press

0.34

 publication

0.26

 writing

0.26

 publishing

0.26

press

0.24

yet

0.23

_press

0.22

publication

0.22

 PRESS

0.21

 presses

0.21

Activations Density 0.026%

phrases indicating a specific timeframe or context in the writing

No Comments

No Known Activations