INDEX

Explanations

words related to leadership and leadership roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

usercontent

-0.17

van

-0.15

ãĤ¦ãĤ¹

-0.15

sgi

-0.15

rame

-0.15

 Arte

-0.15

antz

-0.14

apult

-0.14

zw

-0.14

ssc

-0.14

POSITIVE LOGITS

|_

0.14

uhl

0.14

á»ĩ

0.14

alg

0.14

ë£Į

0.14

iT

0.14

,$_

0.13

ÐºÐ¾ÑĢ

0.13

Slo

0.13

atrix

0.13

Activations Density 0.092%

words related to leadership and leadership roles

No Comments

No Known Activations