INDEX

Explanations

details about product recalls and safety hazards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

woff

-0.18

agnost

-0.17

aea

-0.15

leston

-0.15

eliac

-0.15

RING

-0.15

ring

-0.14

 dest

-0.14

ather

-0.14

hoe

-0.14

POSITIVE LOGITS

 Consumer

0.25

Cri

0.22

cri

0.21

CP

0.21

 consumer

0.21

 suff

0.21

Consumer

0.20

Cri

0.20

CP

0.20

cps

0.20

Activations Density 0.020%

details about product recalls and safety hazards

No Comments

No Known Activations