INDEX

Explanations

references to "those" in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 itself

-0.15

enstein

-0.15

 outset

-0.14

ä¸»äºº

-0.14

those

-0.14

Ø§ÙĨÙĩ

-0.14

izzes

-0.14

orig

-0.14

bild

-0.14

esktop

-0.13

POSITIVE LOGITS

who

0.39

 same

0.29

curity

0.29

who

0.28

 whom

0.28

 kinds

0.26

 whose

0.25

few

0.24

Who

0.23

zelf

0.22

Activations Density 0.058%

references to "those" in varying contexts

No Comments

No Known Activations