INDEX

Explanations

locations and institutions related to educational or professional achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

omik

-0.18

Ð½Ð¸Ð½

-0.17

aroo

-0.15

 Charlottesville

-0.15

aret

-0.15

anik

-0.14

upal

-0.14

·

-0.14

 gains

-0.14

bins

-0.14

POSITIVE LOGITS

 Angelo

0.23

 Benedict

0.21

 Harding

0.20

 Malone

0.20

 Madonna

0.19

Naz

0.19

 Lips

0.19

 Eastern

0.19

Emb

0.19

 Ferr

0.19

Activations Density 0.073%

locations and institutions related to educational or professional achievements

No Comments

No Known Activations