INDEX

Explanations

mentions of various types of stores and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Hospitals

-0.18

 hospitals

-0.16

$MESS

-0.15

èħ¾

-0.15

ëı

-0.14

.RunWith

-0.14

ziej

-0.14

à¸§à¸¥

-0.14

 hospital

-0.14

/Instruction

-0.14

POSITIVE LOGITS

front

0.35

keeper

0.34

keepers

0.32

-front

0.30

owner

0.29

pe

0.28

owners

0.28

éĵº

0.26

 fronts

0.26

 chain

0.25

Activations Density 0.066%

mentions of various types of stores and locations

No Comments

No Known Activations