INDEX

Explanations

references to academic research and studies on contentious topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

loh

-0.16

ITEM

-0.14

razier

-0.14

 Balance

-0.14

/order

-0.13

 Garden

-0.13

hsi

-0.13

bÄĽh

-0.13

iloc

-0.13

 balance

-0.13

POSITIVE LOGITS

apgolly

0.18

.scalablytyped

0.15

.until

0.15

igers

0.15

.opensource

0.14

åł±

0.13

eniable

0.13

 pÅĻep

0.13

ajas

0.13

ILES

0.13

Activations Density 0.079%

references to academic research and studies on contentious topics

No Comments

No Known Activations