INDEX

Explanations

instances and variations of the word "present" and its forms, indicating a focus on the act of presentation or conveying information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eras

-0.17

aktu

-0.17

erator

-0.15

ilde

-0.14

 spare

-0.14

age

-0.14

plevel

-0.14

 Ø¨Ø±Ø¯

-0.14

ITE

-0.14

cie

-0.14

POSITIVE LOGITS

 ÑģÐ¾Ð±Ð¾Ð¹

0.21

CLUDING

0.18

ively

0.17

ÐµÐ´Ð°Ð³

0.16

ĤŃ

0.16

eÄį

0.15

tif

0.15

iÅ¾

0.14

voke

0.14

wk

0.14

Activations Density 0.056%

instances and variations of the word "present" and its forms, indicating a focus on the act of presentation or conveying information

No Comments

No Known Activations