INDEX

Explanations

instances of the pronouns "it" and "is."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

duino

-0.15

estro

-0.15

ãĥ³ãĥĶ

-0.15

ENUM

-0.14

iculture

-0.14

isable

-0.13

 setAddress

-0.13

quit

-0.13

alyzer

-0.13

apos

-0.13

POSITIVE LOGITS

 trans

0.24

 apart

0.19

 soon

0.17

mus

0.16

 fair

0.16

trans

0.16

 Trans

0.15

aug

0.15

ivery

0.15

orf

0.15

Activations Density 0.050%

instances of the pronouns "it" and "is."

No Comments

No Known Activations