INDEX

Explanations

phrases that indicate strain, burden, or impact on systems or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

otas

-0.17

owing

-0.16

atsu

-0.16

Ð¾ÑĤÐ°

-0.16

ota

-0.15

nest

-0.15

isti

-0.15

OTA

-0.14

Ľi

-0.14

POSITIVE LOGITS

 strain

0.33

dam

0.30

 dent

0.26

 strains

0.26

Dam

0.26

lid

0.25

 brakes

0.23

dam

0.22

 brake

0.22

Activations Density 0.033%

phrases that indicate strain, burden, or impact on systems or individuals

No Comments

No Known Activations