INDEX

Explanations

references to significant historical figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Rosenstein

-0.15

ÑĢÑıÐ´Ñĥ

-0.14

 Simmons

-0.14

arer

-0.14

 Overall

-0.14

Gew

-0.14

 Cassidy

-0.14

lights

-0.14

elling

-0.14

enger

-0.14

POSITIVE LOGITS

 similarly

0.28

 likewise

0.23

 Similarly

0.20

Similarly

0.19

 ÑĤÐµÐ¶

0.18

Ð°ÑĢÑĩ

0.17

 Likewise

0.17

 ebenfalls

0.17

Lik

0.15

rych

0.14

Activations Density 0.138%

references to significant historical figures and events

No Comments

No Known Activations