INDEX

Explanations

references to the term "Indian" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

olon

-0.19

inger

-0.17

tainment

-0.16

entai

-0.16

elon

-0.15

inator

-0.15

aternity

-0.15

amiento

-0.14

Zug

-0.14

REFIX

-0.14

POSITIVE LOGITS

apolis

0.33

 Ocean

0.23

OLA

0.20

ised

0.20

ola

0.19

ized

0.19

 Wells

0.17

Ocean

0.17

oe

0.17

apol

0.17

Activations Density 0.012%

references to the term "Indian" and related variations

No Comments

No Known Activations