INDEX

Explanations

locations and geographic references

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

uby

-0.18

 luder

-0.17

imson

-0.17

TypeID

-0.15

å¢ĵ

-0.15

æĪ·

-0.15

Occurred

-0.14

æŀ

-0.14

ìĤ¼

-0.14

å¼

-0.14

POSITIVE LOGITS

Fla

0.38

 Mich

0.34

 Calif

0.33

Va

0.32

 Colo

0.31

Ala

0.30

Ga

0.30

Ind

0.29

Md

0.29

Ore

0.28

Activations Density 0.085%

locations and geographic references

No Comments

No Known Activations