INDEX

Explanations

references to significant violent events and their implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igators

-0.15

leh

-0.15

 Whip

-0.15

-0.14

 Palace

-0.14

 Petro

-0.13

arsed

-0.13

 Ø§ØµÙĦØ§ØŃ

-0.13

 Orleans

-0.13

ugar

-0.13

POSITIVE LOGITS

 Pakistan

0.28

 Pakistani

0.26

Pakistan

0.26

CIA

0.24

ISI

0.24

 drone

0.22

Bin

0.22

bin

0.22

 Predator

0.22

AQ

0.22

Activations Density 0.024%

references to significant violent events and their implications

No Comments

No Known Activations