INDEX

Explanations

references to corporate leadership roles, specifically positions of CEO

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ð¾ÑĢÐ¾Ð²

-0.17

nee

-0.17

Ð¶Ð¸

-0.16

å£«

-0.15

pie

-0.15

arella

-0.15

ning

-0.15

yan

-0.14

yc

-0.14

Ã¼ck

-0.14

POSITIVE LOGITS

icker

0.15

ocoder

0.15

yonel

0.14

phis

0.14

¥Ĳ

0.14

-builder

0.14

/license

0.14

 Vall

0.14

ï¸ı

0.14

Activations Density 0.008%

references to corporate leadership roles, specifically positions of CEO

No Comments

No Known Activations