INDEX

Explanations

terms related to peace and peacebuilding activities

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

Not in Any Lists

No Comments

Negative Logits

luÅ¾

-0.16

lage

-0.16

sein

-0.15

uncture

-0.15

redd

-0.14

ndo

-0.14

YNC

-0.14

 dÃ¼

-0.14

çĽĸ

-0.14

lia

-0.14

POSITIVE LOGITS

keeping

0.29

ably

0.28

able

0.25

keepers

0.23

ful

0.23

fully

0.22

keeper

0.22

FUL

0.22

Maker

0.21

eful

0.20

Activations Density 0.015%

terms related to peace and peacebuilding activities

No Comments

No Known Activations