INDEX

Explanations

phrases containing the word "at" used 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

æ´¥

-0.16

eld

-0.16

isco

-0.15

GLOBALS

-0.15

kers

-0.15

ÅĻÃŃd

-0.15

nist

-0.15

eft

-0.14

ÃŃt

-0.14

owy

-0.14

POSITIVE LOGITS

 face

0.24

 times

0.23

 best

0.22

 worst

0.18

 worse

0.17

best

0.17

 heart

0.17

buz

0.16

heart

0.16

 present

0.16

Activations Density 0.066%

phrases containing the word "at" used in various contexts

No Comments

No Known Activations