INDEX

Explanations

phrases that indicate synergy or perfection 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

aska

-0.16

usan

-0.16

ãģ¬

-0.15

frage

-0.14

oids

-0.14

avatel

-0.14

immel

-0.14

ounded

-0.14

_FATAL

-0.14

aland

-0.14

POSITIVE LOGITS

 embodiment

0.25

 ultimate

0.25

 equivalent

0.24

poster

0.24

 poster

0.23

 definition

0.23

 Equivalent

0.22

 epit

0.21

 king

0.21

 answer

0.21

Activations Density 0.148%

phrases that indicate synergy or perfection in various contexts

No Comments

No Known Activations