INDEX

Explanations

terms related to prophecy and predictions

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

arius

-0.18

antino

-0.16

ilian

-0.16

Ð°ÑĢÐ¸

-0.16

illez

-0.15

rious

-0.15

Ã¼len

-0.15

arian

-0.14

kul

-0.14

aille

-0.14

POSITIVE LOGITS

etic

0.42

etically

0.35

etics

0.31

ets

0.30

Ã©tique

0.30

esis

0.30

sis

0.29

Ã©t

0.29

Ã©tica

0.28

isis

0.27

Activations Density 0.082%

terms related to prophecy and predictions

No Comments

No Known Activations