INDEX

Explanations

abbreviations and identifiers related to geographic locations and entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

edImage

-0.15

*.

-0.14

–

-0.13

*.

-0.13

obus

-0.13

uu

-0.13

iele

-0.13

 ãĢĤ

-0.13

ango

-0.13

ific

-0.13

POSITIVE LOGITS

.,

0.38

./

0.32

.;

0.28

.),

0.26

.,↵

0.25

.).↵↵

0.25

.:

0.24

.;↵

0.23

.ï¼ı

0.22

.).

0.22

Activations Density 0.289%

abbreviations and identifiers related to geographic locations and entities

No Known Activations