INDEX

Explanations

instances of conversational markers and interjections indicating agreement or confirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

">//

-0.16

icare

-0.15

ÏĢÎµÎ¹

-0.14

 trainable

-0.14

ellido

-0.14

naz

-0.14

wcs

-0.13

NavController

-0.13

incess

-0.13

 æľ¨

-0.13

POSITIVE LOGITS

dere

0.16

 derec

0.16

Ð°ÑĢÐ°Ð¼ÐµÑĤ

0.15

mos

0.15

askell

0.15

udur

0.14

.hh

0.14

sar

0.13

 meaning

0.13

ance

0.13

Activations Density 0.130%

instances of conversational markers and interjections indicating agreement or confirmation

No Comments

No Known Activations