INDEX

Explanations

mentions of researchers and their credentials or affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iterals

-0.16

Å¾ÃŃ

-0.16

 à¹Ĩ

-0.15

 Slut

-0.15

.annotate

-0.15

ÑīÐ¸

-0.15

Įĵ

-0.14

ergy

-0.14

rvine

-0.14

yonel

-0.14

POSITIVE LOGITS

 Archae

0.20

 archae

0.19

 archaeological

0.18

 indiv

0.16

 paste

0.15

 virtual

0.15

 Paleo

0.15

arch

0.15

contra

0.15

Activations Density 0.035%

mentions of researchers and their credentials or affiliations

No Comments

No Known Activations