INDEX

Explanations

proper nouns, particularly related to locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

celik

-0.16

afil

-0.15

 helicopt

-0.15

viso

-0.15

lij

-0.15

olist

-0.14

ÏģÎ±ÏĤ

-0.13

Å¡ti

-0.13

efa

-0.13

>NN

-0.13

POSITIVE LOGITS

0.55

0.41

–

0.29

 -↵

0.27

--

0.26

_-_

0.24

{-

0.23

 âĪĴ

0.22

()-

0.21

 -↵↵

0.21

Activations Density 0.175%

proper nouns, particularly related to locations and organizations

No Comments

No Known Activations