INDEX

Explanations

phrases that indicate academic degrees and fields of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ãģ£ãģį

-0.16

thood

-0.15

-cultural

-0.14

issement

-0.14

Equality

-0.14

lland

-0.14

noc

-0.14

 leer

-0.14

VECTOR

-0.14

ularity

-0.14

POSITIVE LOGITS

 Science

0.32

 science

0.30

 Arts

0.29

Science

0.28

 Laws

0.27

 arts

0.26

science

0.23

 laws

0.22

 Ð½Ð°ÑĥÐº

0.18

 sciences

0.18

Activations Density 0.008%

phrases that indicate academic degrees and fields of study

No Comments

No Known Activations