INDEX

Explanations

mentions of education and related educational concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

laus

-0.20

bis

-0.17

acl

-0.15

eto

-0.15

azzi

-0.14

stones

-0.14

stance

-0.14

acha

-0.14

term

-0.13

POSITIVE LOGITS

ally

0.26

caÃ§Ã£o

0.21

ALLY

0.18

ainment

0.16

ystem

0.16

ATIONAL

0.16

ozor

0.15

/Instruction

0.15

omite

0.15

tainment

0.15

Activations Density 0.051%

mentions of education and related educational concepts

No Comments

No Known Activations