INDEX

Explanations

references to U.S. national security and military policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

mont

-0.14

azÄ±

-0.14

 Million

-0.13

tails

-0.13

 Wade

-0.13

yem

-0.13

rette

-0.13

ÑĤÐ¾Ñĩ

-0.13

egal

-0.12

inem

-0.12

POSITIVE LOGITS

 foreign

0.68

 Foreign

0.58

foreign

0.56

Foreign

0.53

 FOREIGN

0.49

_foreign

0.39

 foreigners

0.37

 diplomacy

0.33

 dipl

0.32

 policy

0.30

Activations Density 0.203%

references to U.S. national security and military policies

No Comments

No Known Activations