INDEX

Explanations

instances of the word "Am"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

eum

-0.16

onet

-0.16

enko

-0.16

pas

-0.15

ean

-0.15

éĽĦ

-0.15

point

-0.14

pa

-0.14

points

-0.14

onen

-0.14

POSITIVE LOGITS

plitude

0.28

igos

0.27

ended

0.26

ateurs

0.25

alg

0.25

ateur

0.24

sterdam

0.24

iens

0.24

usement

0.23

igo

0.22

Activations Density 0.016%

instances of the word "Am"

No Comments

No Known Activations