INDEX

Explanations

references to plot developments or character revelations in a series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ŀ

-0.17

-0.16

Gy

-0.14

_MAC

-0.14

TINGS

-0.14

 deficiency

-0.14

 íĸīìłķ

-0.13

odus

-0.13

POSITIVE LOGITS

PLL

0.34

PLL

0.30

pll

0.28

 Pretty

0.26

pll

0.25

 Hanna

0.24

Tro

0.24

Tro

0.23

Pretty

0.23

 Spencer

0.22

Activations Density 0.003%

references to plot developments or character revelations in a series

No Comments

No Known Activations