INDEX

Explanations

frequency and context of key verbs and pronouns that suggest actions or relationships in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

orer

-0.17

rei

-0.15

Cle

-0.14

ignon

-0.14

Ð¼ÐµÑĢÐ¸Ðº

-0.14

ellig

-0.14

enty

-0.14

ãĥ³ãĥĶ

-0.14

erald

-0.14

rox

-0.14

POSITIVE LOGITS

.spin

0.16

Ã¡bado

0.16

.scalablytyped

0.15

undy

0.15

á»¥c

0.15

rowable

0.15

à¤§à¤°

0.14

Ecc

0.14

ÑıÑĩ

0.14

VIC

0.13

Activations Density 0.011%

frequency and context of key verbs and pronouns that suggest actions or relationships in the text

No Comments

No Known Activations