INDEX

Explanations

references to significant historical events or figures related to World War II

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

sey

-0.15

hani

-0.15

ì°°

-0.15

ucus

-0.14

tic

-0.14

_HOT

-0.14

ãģ«åĲĳ

-0.14

lisi

-0.14

Anc

-0.14

nia

-0.14

POSITIVE LOGITS

 Hitler

0.23

Hit

0.19

 Revision

0.17

 Nazi

0.17

NS

0.17

Hit

0.17

 Blitz

0.16

 Adolf

0.15

Activations Density 0.099%

references to significant historical events or figures related to World War II

No Comments

No Known Activations