INDEX

Explanations

comparative phrases and expressions of similarity

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

dorf

-0.16

amen

-0.15

astle

-0.15

itals

-0.15

rch

-0.14

æĹ¢

-0.14

 zwar

-0.14

ivec

-0.14

 accordingly

-0.14

urdu

-0.14

POSITIVE LOGITS

 anything

0.38

anything

0.31

 Anything

0.27

Anything

0.25

 anywhere

0.21

 much

0.19

 necessarily

0.19

much

0.18

 vice

0.17

 versa

0.16

Activations Density 0.044%

comparative phrases and expressions of similarity

No Comments

No Known Activations