INDEX

Explanations

phrases and expressions related to possibility and options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ernes

-0.18

à¸Ńà¹Ģà¸£

-0.16

awan

-0.15

ä¸ĢåĮº

-0.15

raya

-0.14

ÐµÑı

-0.14

ÅĽci

-0.14

ilton

-0.14

andr

-0.13

.Normalize

-0.13

POSITIVE LOGITS

 Impossible

0.16

avicon

0.15

 easy

0.14

pps

0.14

ishlist

0.14

athi

0.14

çĺ

0.14

apol

0.14

è¶Ĭ

0.14

Activations Density 0.204%

phrases and expressions related to possibility and options

No Comments

No Known Activations