INDEX

Explanations

the frequency of the word "every" 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ths

-0.17

ury

-0.17

aget

-0.16

 Days

-0.16

umb

-0.15

-days

-0.15

icable

-0.15

teen

-0.14

ëªħìĿĺ

-0.14

one

-0.14

POSITIVE LOGITS

 chance

0.24

 single

0.20

-single

0.20

day

0.19

 year

0.19

 time

0.18

 night

0.18

 Chance

0.17

 month

0.17

.single

0.17

Activations Density 0.029%

the frequency of the word "every" in various contexts

No Comments

No Known Activations