INDEX

Explanations

terms related to exports and export processes

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

hood

-0.17

angi

-0.16

hole

-0.16

ening

-0.16

ye

-0.15

oud

-0.15

iper

-0.15

iac

-0.14

ustr

-0.14

unda

-0.14

POSITIVE LOGITS

/import

0.34

ation

0.32

-import

0.25

ers

0.23

ting

0.22

ations

0.22

 kháº©u

0.22

able

0.21

ters

0.20

aciÃ³n

0.19

Activations Density 0.010%

terms related to exports and export processes

No Comments

No Known Activations