INDEX

Explanations

references to authors or contributors in academic or scholarly contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

edii

-0.17

Ã©v

-0.15

ames

-0.15

rodu

-0.15

plates

-0.14

ound

-0.13

PREC

-0.13

heim

-0.13

kup

-0.13

ento

-0.13

POSITIVE LOGITS

usch

0.16

Ã±ana

0.15

usu

0.15

 Entries

0.14

igkeit

0.14

utut

0.14

AGED

0.13

ãĥ£

0.13

âĨ

0.13

Activations Density 0.005%

references to authors or contributors in academic or scholarly contexts

No Comments

No Known Activations