INDEX

Explanations

references to time periods and historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

raith

-0.14

 tomorrow

-0.14

 Binding

-0.14

singleton

-0.14

onde

-0.14

ÑĨÐ¸Ðº

-0.14

thur

-0.14

ê¹¨

-0.14

Specifier

-0.14

 binding

-0.13

POSITIVE LOGITS

 late

0.34

 early

0.30

late

0.30

 throughout

0.25

early

0.25

 beginning

0.23

mid

0.22

 Throughout

0.21

Late

0.21

Throughout

0.20

Activations Density 0.196%

references to time periods and historical events

No Comments

No Known Activations