INDEX

Explanations

explicit references to military actions and tactics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

abin

-0.18

adia

-0.16

VRT

-0.16

 Ø¯Ø§Ø®ÙĦÛĮ

-0.15

 okres

-0.15

Ø±ÙĤ

-0.15

atoi

-0.15

ADR

-0.15

apos

-0.14

 unintended

-0.14

POSITIVE LOGITS

 attack

0.56

 attacks

0.45

attack

0.41

 Attack

0.39

 assault

0.38

 strike

0.34

 Attacks

0.34

attacks

0.33

 assaults

0.33

 ATTACK

0.33

Activations Density 0.200%

explicit references to military actions and tactics

No Comments

No Known Activations