INDEX

Explanations

references to historical events and their narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

afone

-0.18

Î½ÎµÎ¹

-0.14

 Kafka

-0.14

ogl

-0.14

mÃ¡n

-0.13

utches

-0.13

dialogs

-0.13

ãĥ«ãĥī

-0.13

orno

-0.13

zÃ¡

-0.13

POSITIVE LOGITS

 historians

0.60

 histor

0.57

 historian

0.55

 Histor

0.49

 History

0.48

 history

0.47

 hist

0.47

 Hist

0.45

histor

0.44

 Historical

0.44

Activations Density 0.260%

references to historical events and their narratives

No Comments

No Known Activations

references to historical events and their narratives

No Comments

No Known Activations