INDEX

Explanations

text related to job announcements and editorial positions

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

 Australians

-0.18

Brit

-0.16

Telefone

-0.15

 Auss

-0.15

 synth

-0.15

 brit

-0.15

 Belg

-0.14

 belg

-0.14

Sno

-0.14

uk

-0.14

POSITIVE LOGITS

 Latin

0.35

Latin

0.31

 Latino

0.26

 Chic

0.26

 LATIN

0.25

Ð»Ð°ÑĤÐ¸

0.24

 Puerto

0.24

Lat

0.24

 latin

0.24

 Hispanic

0.23

Activations Density 0.274%

text related to job announcements and editorial positions

No Comments

No Known Activations