INDEX

Explanations

references to the United States and its geopolitical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ToWorld

-0.16

-0.15

usch

-0.15

 Dome

-0.15

thon

-0.15

rung

-0.14

trim

-0.14

stvÃŃ

-0.14

 trim

-0.14

akespeare

-0.13

POSITIVE LOGITS

/world

0.20

-Israel

0.19

/E

0.18

-wide

0.18

VI

0.17

 Ø§ÙĦØ£ÙħØ±ÙĬÙĥÙĬØ©

0.17

 Ø¢ÙħØ±ÛĮÚ©Ø§

0.17

 Virgin

0.17

 Ø§ÙĦÙħØªØŃØ¯Ø©

0.17

Activations Density 0.096%

references to the United States and its geopolitical context

No Comments

No Known Activations