INDEX

Explanations

references to historical events and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Pai

-0.15

èĤĸ

-0.15

oder

-0.14

gid

-0.14

umd

-0.14

atura

-0.14

heten

-0.13

 Distributed

-0.13

 advis

-0.13

dn

-0.13

POSITIVE LOGITS

 history

0.26

history

0.20

 History

0.20

/history

0.20

-history

0.19

ISTORY

0.18

istory

0.18

 HISTORY

0.18

 Geschichte

0.18

History

0.17

Activations Density 0.107%

references to historical events and contexts

No Comments

No Known Activations