INDEX

Explanations

references to the act of pushing or placing distance between individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eries

-0.15

Ä±rÄ±

-0.15

orld

-0.14

esk

-0.14

-svg

-0.14

nero

-0.14

erland

-0.14

 ViewBag

-0.14

indsight

-0.14

gment

-0.13

POSITIVE LOGITS

 pushes

0.21

 pushed

0.21

 Push

0.20

 push

0.20

 pushing

0.19

 into

0.19

 onto

0.18

.Push

0.18

Push

0.17

 aside

0.17

Activations Density 0.073%

references to the act of pushing or placing distance between individuals

No Comments

No Known Activations