INDEX

Explanations

statements regarding political neutrality and denial of endorsement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

alytics

-0.16

-0.15

Ã¤lt

-0.15

ocket

-0.15

arin

-0.14

ohn

-0.14

thern

-0.14

 Investor

-0.14

 ARGS

-0.14

ifi

-0.13

POSITIVE LOGITS

nor

0.40

nor

0.29

Nor

0.27

Nor

0.25

NOR

0.24

any

0.20

ä»»ä½ķ

0.19

ENDOR

0.18

 anyone

0.18

ANY

0.16

Activations Density 0.059%

statements regarding political neutrality and denial of endorsement

No Comments

No Known Activations