INDEX

Explanations

references to real estate and related professional terms

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

 rough

-0.18

rom

-0.18

uegos

-0.15

rough

-0.15

 Rough

-0.15

uele

-0.15

ughty

-0.14

rupa

-0.14

Ð¾ÑĢÐ¾Ð·

-0.14

iz

-0.14

POSITIVE LOGITS

Ð¸Ð¹

0.17

iaux

0.16

berger

0.15

 Minority

0.15

ÑĩÑĥ

0.15

fcn

0.14

ajar

0.14

 Convention

0.14

cea

0.14

Î½Îµ

0.14

Activations Density 0.063%

references to real estate and related professional terms

No Comments

No Known Activations