INDEX

Explanations

quantitative data related to public opinion or awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

obi

-0.15

 åĽ½å®¶

-0.14

 Islamabad

-0.14

PEAT

-0.14

-0.13

aml

-0.13

 Norris

-0.13

éĢĨ

-0.13

POSITIVE LOGITS

US

0.23

 Donald

0.21

UN

0.21

 sanctions

0.20

UNS

0.19

Lav

0.19

Hou

0.18

 Trump

0.18

Donald

0.18

US

0.17

Activations Density 0.338%

quantitative data related to public opinion or awareness

No Comments

No Known Activations