INDEX

Explanations

references to education and professional training experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 currently

-0.17

æĹ¢çĦ¶

-0.16

åħ¨çĲĥ

-0.15

 yesterday

-0.14

æĺ¨

-0.14

 dnes

-0.14

çİ°åľº

-0.14

 lately

-0.14

 recently

-0.14

 tonight

-0.14

POSITIVE LOGITS

 eventually

0.35

 Eventually

0.33

 earning

0.31

 until

0.29

Eventually

0.29

 becoming

0.28

 before

0.28

 winning

0.28

 eventual

0.28

until

0.24

Activations Density 0.267%

references to education and professional training experiences

No Comments

No Known Activations

references to education and professional training experiences

No Comments

No Known Activations