INDEX

Explanations

references to specific geographic locations, particularly those associated with the name "Dur."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

chia

-0.17

 dist

-0.16

ãĥ¬ãĥĥãĥĪ

-0.15

agar

-0.14

 Winston

-0.14

errat

-0.14

 Sunrise

-0.14

Ts

-0.13

jad

-0.13

.Blocks

-0.13

POSITIVE LOGITS

amework

0.20

-lasting

0.17

maid

0.16

dur

0.16

inja

0.15

uxe

0.15

azzo

0.15

umo

0.15

amaz

0.15

AMESPACE

0.15

Activations Density 0.009%

references to specific geographic locations, particularly those associated with the name "Dur."

No Comments

No Known Activations