INDEX

Explanations

words related to linguistics and language studies

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

adero

-0.16

ÏģÏį

-0.15

krÃ¡t

-0.15

Dud

-0.15

ãĥ³ãĥĨ

-0.14

itant

-0.14

agrid

-0.14

Ķ

-0.14

ç·Ĵ

-0.14

 verso

-0.14

POSITIVE LOGITS

istics

0.32

istic

0.22

istically

0.20

ering

0.18

ual

0.17

ua

0.16

 franca

0.16

 Ø²Ø¯

0.16

 ling

0.16

-cultural

0.16

Activations Density 0.010%

words related to linguistics and language studies

No Comments

No Known Activations

words related to linguistics and language studies

No Comments

No Known Activations