INDEX

Explanations

connections to military applications and influence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

undra

-0.17

apore

-0.15

alous

-0.14

ilos

-0.14

istrat

-0.14

ingt

-0.14

isle

-0.14

abis

-0.14

chaft

-0.14

.synthetic

-0.14

POSITIVE LOGITS

inic

0.16

/mod

0.15

 demand

0.14

 ZÃ¡p

0.14

ICC

0.14

Cyr

0.14

vest

0.14

Fur

0.13

 intact

0.13

 caveat

0.13

Activations Density 0.448%

connections to military applications and influence

No Comments

No Known Activations