INDEX

Explanations

references to rankings, awards, and repeated achievements in education and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

UpdateTime

-0.15

èĸĦ

-0.14

.throw

-0.14

-kind

-0.14

asin

-0.14

hammad

-0.14

rung

-0.14

æ¡Ĳ

-0.14

fern

-0.14

Ã¼re

-0.13

POSITIVE LOGITS

 consecutive

0.64

 straight

0.60

 consec

0.55

straight

0.53

è¿ŀ

0.53

 consect

0.52

 Straight

0.51

 continuous

0.49

 successive

0.47

Straight

0.47

Activations Density 0.131%

references to rankings, awards, and repeated achievements in education and performance metrics

No Comments

No Known Activations