INDEX

Explanations

references to the term "bat" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

hoff

-0.20

Vit

-0.18

orgh

-0.17

vit

-0.16

à¸±à¸¢

-0.16

sad

-0.16

ìķĻ

-0.15

bia

-0.15

á»ħ

-0.15

ertz

-0.14

POSITIVE LOGITS

htub

0.26

Bat

0.20

tement

0.19

 Rouge

0.19

ting

0.19

lle

0.19

Bat

0.19

anical

0.17

wing

0.17

itle

0.17

Activations Density 0.010%

references to the term "bat" in various contexts

No Comments

No Known Activations