INDEX

Explanations

terms related to historical contexts and events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 history

-0.35

 History

-0.33

History

-0.32

_history

-0.32

 histories

-0.31

åİĨåı²

-0.30

 Historical

-0.30

history

-0.30

 historia

-0.30

 HISTORY

-0.28

POSITIVE LOGITS

/current

0.25

æĤł

0.24

 accuracy

0.21

ÚĨÙĩ

0.19

-fiction

0.19

-marker

0.18

 context

0.18

 Marker

0.17

 accur

0.17

chw

0.17

Activations Density 0.014%

terms related to historical contexts and events

No Known Activations