INDEX

Explanations

quotes or dialog in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑıÐ½

-0.19

aset

-0.17

icket

-0.17

abase

-0.16

ivia

-0.15

PointerException

-0.14

regor

-0.14

ashtra

-0.14

ickets

-0.14

 AsyncCallback

-0.13

POSITIVE LOGITS

rie

0.18

oppers

0.17

 Harley

0.16

ä¿Ĭ

0.15

SOR

0.15

}elseif

0.14

Ced

0.14

ige

0.14

vere

0.14

Activations Density 0.006%

quotes or dialog in the text

No Comments

No Known Activations