INDEX

Explanations

references to future plans and upcoming events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

IENTATION

-0.15

ntag

-0.15

uit

-0.15

pie

-0.14

iese

-0.14

Ĭ¶

-0.13

orts

-0.13

äº²

-0.13

 Accounting

-0.13

 increasingly

-0.13

POSITIVE LOGITS

.scalablytyped

0.16

.DropDown

0.15

è½®

0.14

resco

0.14

YC

0.14

Ð»ÐµÐ¶

0.14

ovice

0.14

 -*-č↵

0.13

rea

0.13

 Bounty

0.13

Activations Density 0.150%

references to future plans and upcoming events

No Comments

No Known Activations