INDEX

Explanations

terms related to language and bilingualism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

istol

-0.18

mers

-0.18

avis

-0.17

ingly

-0.17

lying

-0.16

lech

-0.16

pling

-0.16

ders

-0.16

Ã©ry

-0.15

ry

-0.15

POSITIVE LOGITS

 spoken

0.27

0.26

 barrier

0.21

auge

0.21

 franca

0.20

.googleapis

0.20

 acquisition

0.19

 Barrier

0.19

 Arts

0.19

-speaking

0.19

Activations Density 0.035%

terms related to language and bilingualism

No Comments

No Known Activations