INDEX

Explanations

variations of the word "the" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 midst

-0.17

agli

-0.14

clusions

-0.14

 sake

-0.13

 behalf

-0.13

osi

-0.13

ovu

-0.13

ivities

-0.13

illance

-0.13

ä¿

-0.13

POSITIVE LOGITS

 only

0.31

oret

0.26

 odds

0.25

 focus

0.25

 question

0.24

aim

0.23

 stakes

0.23

 amount

0.23

 mere

0.22

 emphasis

0.22

Activations Density 0.964%

variations of the word "the" in different contexts

No Comments

No Known Activations