INDEX

Explanations

names and titles related to political figures and their affiliations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abble

-0.17

imli

-0.16

ÑĮÑİ

-0.15

ayi

-0.14

yne

-0.14

 Kraft

-0.14

place

-0.14

vale

-0.14

.mixin

-0.14

esi

-0.13

POSITIVE LOGITS

ognition

0.16

á»Ļn

0.15

enville

0.14

ç²¾ç¥ŀ

0.14

 spit

0.14

asher

0.14

ÎºÎ·

0.14

andid

0.13

ÑĻ

0.13

Activations Density 0.014%

names and titles related to political figures and their affiliations

No Comments

No Known Activations