INDEX

Explanations

references to graduation or educational achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iard

-0.19

å¸¯

-0.16

uze

-0.15

ing

-0.15

bons

-0.15

ãĥ³ãĥī

-0.15

chap

-0.15

ëł¥ìĿĦ

-0.15

åĳ½

-0.15

iw

-0.15

POSITIVE LOGITS

uated

0.34

uation

0.33

uate

0.32

uates

0.30

ually

0.29

ual

0.27

uating

0.25

IENT

0.23

iente

0.20

uations

0.19

Activations Density 0.008%

references to graduation or educational achievements

No Comments

No Known Activations