INDEX

Explanations

references to the Cold War and related geopolitical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

eson

-0.18

enet

-0.15

upy

-0.15

iliz

-0.15

ultip

-0.14

clair

-0.14

 Bols

-0.14

 PlzeÅĪ

-0.14

 Clair

-0.14

Dol

-0.14

POSITIVE LOGITS

mund

0.17

pis

0.15

stuff

0.15

cit

0.15

strip

0.15

 Ð´ÑĥÑĪ

0.15

erral

0.14

-era

0.14

ı

0.14

alic

0.14

Activations Density 0.009%

references to the Cold War and related geopolitical topics

No Comments

No Known Activations