INDEX

Explanations

references to materials and their properties or implications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eg

-0.20

amilia

-0.19

ess

-0.17

esModule

-0.15

opus

-0.15

addtogroup

-0.15

eba

-0.15

egl

-0.14

oders

-0.14

azz

-0.13

POSITIVE LOGITS

ized

0.23

istic

0.21

izing

0.21

ize

0.20

UnderTest

0.19

ization

0.18

istically

0.18

è³ª

0.18

ity

0.18

icious

0.18

Activations Density 0.033%

references to materials and their properties or implications in various contexts

No Comments

No Known Activations