INDEX

Explanations

references to empires and imperial power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ened

-0.17

etime

-0.16

iversity

-0.16

ening

-0.16

 eens

-0.15

rous

-0.15

erman

-0.15

çĮ

-0.15

acre

-0.15

 Gems

-0.14

POSITIVE LOGITS

-wide

0.15

vlc

0.15

cxx

0.14

 cháº¿

0.14

notify

0.14

ãģªãģĬ

0.14

SSIP

0.14

grand

0.14

amet

0.14

gebn

0.14

Activations Density 0.020%

references to empires and imperial power dynamics

No Comments

No Known Activations