INDEX

Explanations

references to diplomatic missions and negotiations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

celik

-0.18

lotte

-0.16

apan

-0.15

esine

-0.15

 assoc

-0.14

/dataTables

-0.14

 devote

-0.14

irket

-0.14

rong

-0.14

agus

-0.14

POSITIVE LOGITS

 mission

0.23

 missions

0.19

Mission

0.19

 fetch

0.18

mission

0.18

 report

0.18

report

0.17

 representing

0.17

 carrying

0.17

 Fetch

0.17

Activations Density 0.095%

references to diplomatic missions and negotiations

No Comments

No Known Activations