INDEX

Explanations

variations of the word "ar" or "ar" of different compositions or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.27

es

-0.25

ed

-0.25

ec

-0.24

ek

-0.24

enden

-0.23

ela

-0.23

ey

-0.23

ent

-0.22

end

-0.22

POSITIVE LOGITS

beiter

0.26

beiten

0.26

thur

0.24

hyth

0.24

ctica

0.23

oon

0.23

monic

0.21

aptor

0.21

theid

0.20

ithmetic

0.20

Activations Density 0.111%

variations of the word "ar" or "ar" of different compositions or contexts

No Comments

No Known Activations