INDEX

Explanations

references to biblical or religious themes and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

zen

-0.15

whose

-0.15

king

-0.15

iling

-0.15

olver

-0.15

 Wanted

-0.14

at

-0.14

always

-0.13

lesh

-0.13

/display

-0.13

POSITIVE LOGITS

who

0.31

 which

0.31

wh

0.29

qui

0.29

—which

0.26

 WHICH

0.26

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐ¹

0.25

 quienes

0.25

 Ø§ÙĦØ°ÙĬ

0.25

åĵª

0.24

Activations Density 0.049%

references to biblical or religious themes and concepts

No Comments

No Known Activations