INDEX

Explanations

geographical identifiers related to locations and specific places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 AssemblyVersion

-0.15

landa

-0.15

avan

-0.15

imary

-0.14

moz

-0.14

+:+

-0.14

Wunused

-0.14

udev

-0.14

_lineno

-0.14

alytics

-0.14

POSITIVE LOGITS

quam

0.23

aukee

0.21

waukee

0.21

quan

0.21

 Indians

0.19

 Indian

0.18

ippi

0.18

oodle

0.17

qua

0.17

aw

0.16

Activations Density 0.100%

geographical identifiers related to locations and specific places

No Comments

No Known Activations

geographical identifiers related to locations and specific places

No Comments

No Known Activations