INDEX

Explanations

instances of the word "this" and related phrases that reference specific items or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-tab

-0.14

ephy

-0.14

_reporting

-0.14

StackNavigator

-0.13

routeParams

-0.13

OLVE

-0.13

_errno

-0.13

 Jarvis

-0.13

ouri

-0.13

roll

-0.13

POSITIVE LOGITS

Ð½Ð°Ðº

0.15

 Guarantee

0.14

awns

0.14

Ø³Ø¨

0.14

.WinForms

0.14

uddy

0.14

ebb

0.14

oÄŁlu

0.14

.Unicode

0.13

TTY

0.13

Activations Density 0.491%

instances of the word "this" and related phrases that reference specific items or topics

No Comments

No Known Activations